--- name: latex-resume-builder description: >- Builds Abinesh Haridoss's resume as raw LaTeX (.tex) tailored to a job description. Use ONLY when the user wants LaTeX, .tex, or Overleaf output. Do NOT use for Word, .docx, Microsoft Word, Workday, or strict-ATS requests — use word-resume-builder instead. Triggers: LaTeX resume, tex resume, Overleaf, ATS optimize LaTeX. --- # LaTeX Resume Builder — Abinesh Haridoss ## START HERE ### WHEN TO USE THIS SKILL - User asks for **LaTeX**, **.tex**, or **Overleaf** output - User says "compile in Overleaf" or "give me the tex file" - Triggers: LaTeX resume, tex resume, Overleaf, ATS optimize LaTeX ### WHEN NOT TO USE - User wants **Word**, **.docx**, or **Microsoft Word** → use **word-resume-builder** - User mentions **Workday**, **Taleo**, **iCIMS**, **Greenhouse**, **SuccessFactors**, or "strict ATS format" by name → use **word-resume-builder** (specialized for strict-ATS parsers) - User wants PDF only without LaTeX source → ask if they want `.tex` (this skill) or `.docx` (Word skill) ### NON-NEGOTIABLES 1. All **6 sections** in fixed order (Contact → Summary → Professional Experience → Projects → Education → Technical Skills) 2. Fixed job titles, companies, and dates from candidate profile — never invent or change 3. **No fabrication** — reframe real experience only 4. Summary **must state 6+ years** of experience — never use 5+ years 5. **Bold keywords and metrics** in bullets using `\textbf{}` — match baseline template pattern 6. Preserve exact LaTeX preamble, packages, `\location` macro, and geometry (0.3in margins, 10pt lmodern) 7. Exactly **2 pages** when compiled — no page 3, no trailing whitespace 8. **AI-recruiter scoring rubric** (`../shared/scoring-rubric.md`) — project links, complexity framing, open-source language, deduction avoidance ### IF JD MISSING **STOP.** Ask the user to paste the job description (or URL). Do not tailor without a JD. --- ## Reference files (read when tailoring) | When | Read | | --- | --- | | Before any edit | `../shared/candidate-profile.md` — fixed fields, experience index, project pool | | Bullet editing | `../shared/bullet-strategy.md` — Step 0, edit vs add, verbs, page fill | | Before output | `../shared/checklist.md` — single pre-output checklist | | LaTeX structure | **Baseline Template** section below — full starting template | | LaTeX rules | **LaTeX Formatting Reference** section below — macros, anti-patterns, ATS | | **AI-recruiter scoring rubric** | `../shared/scoring-rubric.md` — project selection, complexity framing, open-source language, deduction avoidance | --- ## Primary Workflow When the user provides a **job description** and wants LaTeX output: ### Step 0 — JD gate **STOP** if no JD — ask user to paste it. ### Step 1 — READ candidate profile **READ** `../shared/candidate-profile.md`. Do not invent roles, dates, locations, or employers. ### Step 2 — READ baseline template **READ** **Baseline Template** below. Start from this file for every request. Preserve LaTeX structure (preamble, `\location`, minipage projects, spacing); modify Summary (keep **6+ years**), bullets, Projects, and Technical Skills only. ### Step 3 — WRITE Summary first **WRITE Summary first** — mirror JD role title + **6+ years of experience** + 3–4 themes. Every Experience bullet must reinforce this narrative. ### Step 4 — EDIT bullets **EDIT bullets** using priority: 1. **Minimal edit first** — weave missing JD keywords into existing bullets (one crisp line each) 2. **New bullet only** for true gaps where real work exists — add to most relevant role, distributed across roles 3. **Reorder Technical Skills** — JD tools first; candidate must actually use them See `../shared/bullet-strategy.md` for Step 0 parsing, decision rules, and verb guidance. ### Step 5 — SELECT projects **SELECT projects** from the pool in `../shared/candidate-profile.md`. Preserve minipage project header layout; swap JD-relevant projects when tailoring. ### Step 6 — APPLY scoring rubric **READ** `../shared/scoring-rubric.md` and verify before balancing pages: - Every selected project has its real GitHub link — never omit - No generic/tutorial project framing or names - Project bullets foreground complexity and impact (not just "built X using Y") - Personal repos are self projects — never labeled as open source contributions - Experience bullets show production scale and measurable outcomes - Technical Skills lists only defensible tools; JD Priority-1 keywords appear in bullets too ### Step 7 — BALANCE to exactly 2 pages **BALANCE to exactly 2 pages.** If short, add crisp bullets evenly across roles (reframe real work). If long, trim oldest/least JD-relevant roles first. Never drop a section. ### Step 8 — OUTPUT NOW **OUTPUT NOW:** Return the **complete raw LaTeX** from `\documentclass` through `\end{document}`. - No markdown fences - No commentary unless user asks - User compiles in Overleaf with `pdflatex` --- ## User trigger phrases - "Give me LaTeX for Overleaf for this JD" - "Update my LaTeX resume" - "Tailor my resume in tex" - "ATS optimize my LaTeX resume" If user says "tailor my resume" **without naming format**, ask: **LaTeX (.tex) or Word (.docx)?** ### Required user input ``` I'm applying for this job: [paste job description or URL] ``` Background is embedded in reference files. **Do not ask the user to re-paste work history** unless they want to change roles, dates, or add experience. --- ## Keyword tailoring (summary) | Section | Action | | --- | --- | | Summary | Rewrite first — sets narrative | | Experience | Align with Summary + JD; crisp bullets with `\textbf{}` keywords | | Projects | JD-relevant from pool; preserve minipage layout | | Technical Skills | Reorder; add JD tools candidate actually uses | ### What NEVER to change - Name, contact, URLs - Job titles, companies, dates - Section order and all 6 sections - LaTeX preamble, `\location` macro, geometry, packages - **6+ years** in Summary - Fabricated experience or metrics --- ## LaTeX essentials ### Job header Title left, dates **right-aligned** via `\location{Dates}` on the same line: ```latex \vspace{3mm} \textbf{Full Stack Developer} \location{Mar 2020 -- Sept 2021} \\ \textit{Tanishq \& ProwessIQ Private Limited} \hfill \textit{} \\ \begin{itemize} \item Implemented \textbf{authentication mechanisms} with \textbf{OAuth2 and JWT}... \vspace{1mm} \end{itemize} ``` Never use `\jobentry`. Always use `\textbf{Title} \location{Dates} \\` then `\textit{Company} \hfill \textit{} \\`. ### Spacing rules - Use `\vspace{3mm}` before each role block and `\vspace{1mm}` between bullets inside `itemize` — match baseline template - Use `\location` for job and education date lines - Projects use `\begin{minipage}[t]{\textwidth}` header + `\begin{itemize}` bullets - No trailing spaces on any output line ### Bold rule Bold **JD keywords and metrics** with `\textbf{}` — match baseline template density (tools, frameworks, and numeric results). Full macros, anti-patterns, and ATS rules: **LaTeX Formatting Reference** below. --- ## Page fill strategy (quick reference) **Too much white space:** Add crisp bullets across roles — do not pad with `\vspace` or long paragraphs. **Over 2 pages:** Trim Tanishq → LTIMindtree → … first. Shorten wording; keep Action + Result. Full rules: `../shared/bullet-strategy.md` --- ## DELIVER — final checklist Run `../shared/checklist.md` internally, then confirm: - [ ] All 6 sections present in order - [ ] Summary states **6+ years** experience - [ ] Job titles, companies, dates unchanged from candidate profile - [ ] `\location` job/education headers; minipage project headers - [ ] Exactly 2 pages when compiled - [ ] Raw LaTeX output — no markdown fences --- ## Output format **Default:** Raw LaTeX only — full document, no fences, no preamble explanation. **If user asks for explanation:** After LaTeX, optionally append a keyword mapping table (JD term → where added). --- ## LaTeX Formatting Reference Read **Baseline Template** below. Apply tailoring to Summary (keep **6+ years**), bullets, Projects, and Technical Skills only. **Never change preamble, packages, geometry, or `\location` macro.** ### Document class and packages (do not change) ```latex \documentclass[a4paper,10pt]{article} \usepackage[utf8]{inputenc} \usepackage{enumitem} \usepackage{geometry} \usepackage[hidelinks]{hyperref} \usepackage{titlesec} \usepackage{parskip} \usepackage{lmodern} \usepackage{fancyhdr} \usepackage{array} \usepackage{multicol} \usepackage{fontawesome} ``` ### Page geometry and macros (do not change) ```latex \geometry{left=0.3in, right=0.3in, top=0.3in, bottom=0.1in} \setlength{\parindent}{0pt} \setlength{\parskip}{0pt} \titlespacing\section{0pt}{5pt plus 2pt minus 2pt}{3pt plus 2pt minus 2pt} \titleformat{\section}{\bfseries\large}{}{0em}{}[\titlerule] \fancypagestyle{plain}{ \fancyhf{} \fancyfoot[C]{\thepage} \renewcommand{\headrulewidth}{0pt} } \setlist[itemize]{noitemsep, topsep=0pt} \newcommand{\location}[1]{\hfill #1} ``` ### Job header pattern ```latex \vspace{3mm} \textbf{LLM Trainer} \location{Sept 2025 -- Present} \\ \textit{Turing} \hfill \textit{} \\ \begin{itemize} \item Designed and deployed LLM training data collection workflows... \vspace{1mm} \end{itemize} ``` ### Education header pattern ```latex \textbf{Master of Science in Computer Science} \location{Aug. 2023 -- 2025} \\ \textit{University of North Texas} \hfill \textit{} \\ ``` ### Project header pattern (minipage) ```latex \begin{minipage}[t]{\textwidth} \textbf{Fraud Folio} \textbar\ \textit{AI, Fraud Detection, Meta Llama 3} \hfill \href{https://github.com/abinesha312/hack_unt_financial_fraud.git}{\faExternalLink} \end{minipage} \begin{itemize} \item Engineered a \textbf{custom fraud detection pipeline}... \vspace{1mm} \end{itemize} \vspace{3mm} ``` ### Section order (fixed — 6 sections) 1. Contact Header 2. Summary (**6+ years** experience line required) 3. Professional Experience (roles 1–6) 4. Projects (minipage headers) 5. Education 6. Technical Skills ### Anti-patterns (never do these) ```latex ❌ \jobentry{...}{...}{...} % old macro — forbidden ❌ \textbf{Title} — Dates \\ % dates must use \location ❌ 1in margins or helvet font % wrong template ❌ 5+ years in Summary % must be 6+ years ✅ \textbf{Title} \location{Dates} \\ \textit{Company} \hfill \textit{} \\ ✅ \vspace{1mm} between bullets inside itemize ✅ minipage project headers with \faExternalLink links ``` ### Typography & length - Latin Modern (lmodern), 10pt, 0.3in side/top margins - Max **2 pages** when compiled - Export via `pdflatex` in Overleaf --- ## Baseline Template Full starting `.tex` — copy verbatim except Summary/bullets/projects/skills tailoring. Summary **must keep 6+ years**. ```latex \documentclass[a4paper,10pt]{article} \usepackage[utf8]{inputenc} \usepackage{enumitem} \usepackage{geometry} \usepackage[hidelinks]{hyperref} \usepackage{titlesec} \usepackage{parskip} \usepackage{lmodern} \usepackage{fancyhdr} \usepackage{array} \usepackage{multicol} \usepackage{fontawesome} \geometry{left=0.3in, right=0.3in, top=0.3in, bottom=0.1in} \setlength{\parindent}{0pt} \setlength{\parskip}{0pt} \titlespacing\section{0pt}{5pt plus 2pt minus 2pt}{3pt plus 2pt minus 2pt} \titleformat{\section}{\bfseries\large}{}{0em}{}[\titlerule] \fancypagestyle{plain}{ \fancyhf{} \fancyfoot[C]{\thepage} \renewcommand{\headrulewidth}{0pt} } \setlist[itemize]{noitemsep, topsep=0pt} \newcommand{\location}[1]{\hfill #1} \begin{document} \begin{center} {\LARGE \textbf{Abinesh Haridoss}} \\ +1 346-823-9553 \textbar\ \href{mailto:abinesha312@gmail.com}{abinesha312@gmail.com} \textbar\ \href{https://github.com/abinesha312}{github.com/abinesha312} \textbar\ \href{https://www.linkedin.com/in/aharido/}{linkedin.com/in/aharido/} \textbar\ \href{https://abineshharidoss.web.app/}{abineshharidoss.web.app/} \end{center} \vspace{-1mm} \section*{Summary} \vspace{1mm} \textbf{Full Stack Engineer} with a Master's in Computer Science and \textbf{6+ years} of experience building and deploying \textbf{enterprise-grade web applications} using \textbf{.NET}, \textbf{C\#}, and modern \textbf{Python frameworks} such as \textbf{FastAPI} and \textbf{Django}. Skilled in developing \textbf{AI-powered features}, integrating \textbf{machine learning models}, and optimizing \textbf{microservice architectures} across cloud platforms including \textbf{AWS}, \textbf{GCP}, and \textbf{Azure}. Proficient in \textbf{Angular}, \textbf{JavaScript}, and database design using \textbf{SQL} and \textbf{PostgreSQL}, with hands-on expertise in \textbf{TDD/BDD}, \textbf{DevOps}, and \textbf{CI/CD automation}. Demonstrated success in leading cross-functional teams, driving \textbf{proof-of-concepts}, and delivering \textbf{AI-driven, scalable solutions} that align with modern design and development best practices. \section*{Professional Experience} \vspace{3mm} \textbf{LLM Trainer} \location{Sept 2025 -- Present} \\ \textit{Turing} \hfill \textit{} \\ \begin{itemize} \item Designed and deployed LLM training data collection workflows with automated \textbf{annotation} and \textbf{validation} stages, improving labeling throughput by \textbf{25\%} and cutting manual review time by \textbf{30\%}. \vspace{1mm} \item Leveraged \textbf{AWS Bedrock} with \textbf{LangChain} and \textbf{LangGraph} to orchestrate multi-modal \textbf{LLM training data} pipelines, boosting data throughput by \textbf{35\%} and enabling regionally distributed dataset collection at scale. \vspace{1mm} \end{itemize} \vspace{3mm} \textbf{AI/ML Engineer} \location{Jul 2025 -- Sept 2025} \\ \textit{Worlds Enterprise Inc.} \hfill \textit{} \\ \begin{itemize} \item Designed and deployed \textbf{agentic AI workflows} with autonomous decision-making capabilities, automating complex pipelines and improving operational \textbf{efficiency by 25\%}. \vspace{1mm} \item Leveraged \textbf{AWS Bedrock} with \textbf{LangChain} and \textbf{LangGraph} to orchestrate multi-modal data pipelines, boosting data throughput by \textbf{35\%} and enabling regionally distributed AI deployments at scale. \vspace{1mm} \item Implemented \textbf{generative AI-driven code assistants} using \textbf{LangFlow} and \textbf{LangSmith} for modular development and debugging, reducing manual coding effort by \textbf{40\%} and accelerating release cycles. \vspace{1mm} \item Engineered and deployed \textbf{high-performance RESTful APIs} using \textbf{FastAPI} with \textbf{asynchronous I/O}, achieving \textbf{low-latency} and \textbf{high-throughput} request handling in production systems. \vspace{1mm} \item Designed \textbf{robust data models and validation layers} with \textbf{Pydantic} in FastAPI, ensuring data integrity, type safety, and fault-tolerant service interactions across microservices. \vspace{1mm} \item Integrated \textbf{SQLAlchemy ORM} for efficient database operations, optimizing query execution and schema management in \textbf{PostgreSQL}-backed FastAPI applications. \end{itemize} \vspace{5mm} \textbf{AI Engineer} \location{Oct 2023 -- May 2025} \\ \textit{University of North Texas} \hfill \textit{} \\ \begin{itemize} \item Engineered advanced \textbf{agentic AI pipelines} at the University of North Texas, integrating \textbf{multi-agent coordination}, \textbf{context-aware reasoning}, and \textbf{workflow orchestration}, improving research automation efficiency by \textbf{30\%}. \vspace{1mm} \item Developed \textbf{generative AI solutions} for \textbf{code synthesis} and \textbf{academic tooling}, reducing implementation time for research prototypes by \textbf{35\%} and accelerating experiment reproducibility. \vspace{1mm} \item Configured and optimized \textbf{MCP server deployments} for distributed AI experiments, enabling secure collaboration, parallel computation, and increasing system throughput by \textbf{25\%}. \vspace{1mm} \item Containerized and automated FastAPI deployments using \textbf{Docker} and \textbf{CI/CD pipelines}, enabling consistent builds, rapid releases, and seamless environment parity. \vspace{1mm} \item Implemented \textbf{structured logging, monitoring, and observability} with FastAPI and \textbf{OpenTelemetry}, improving system reliability and reducing debugging time by \textbf{30\%}. \vspace{1mm} \item Implemented \textbf{multi-GPU training pipelines} leveraging \textbf{PyTorch Distributed}, \textbf{FSDP}, and \textbf{NCCL} for large-scale model parallelism, achieving \textbf{45\% reduction in latency} and \textbf{30\% higher GPU utilization}. \end{itemize} \vspace{5mm} \textbf{Associate Software Developer} \location{Feb 2023 -- Jul 2023} \\ \textit{TransUnion} \hfill \textit{} \\ \begin{itemize} \item Designed a \textbf{microservices}-based credit generation ML model, leveraging additional input fields to improve prediction accuracy by \textbf{70\%}, enabling more reliable risk assessment and credit approvals. \vspace{1mm} \item Spearheaded \textbf{credit-score monitoring} deep learning models using \textbf{PyTorch} and internal DL frameworks, achieving real-time fraud detection with latency under 200ms and improving anomaly recall rates by \textbf{25\%}. \vspace{1mm} \item Integrated a \textbf{GraphQL} API layer into the \textbf{React Native} stack, synchronizing commercial data across five platforms and reducing data-fetching overhead by \textbf{40\%}. \vspace{1mm} \item Implemented \textbf{TypeScript} with a \textbf{micro-frontend} architecture, modularizing the codebase for distributed engineering teams and reducing feature delivery time by \textbf{20\%}. \end{itemize} \vspace{7mm} \textbf{Software Engineer} \location{Oct 2021 -- Feb 2023} \\ \textit{Larsen and Toubro Infotech Mindtree} \hfill \textit{} \\ \begin{itemize} \item Oversaw a team of developers and conducted regular code reviews, ensuring deadlines were met ahead by \textbf{15\%}. \vspace{1mm} \item Engineered distributed caching with \textbf{Redis}, optimizing real-time data access speed by \textbf{3.2x} in benchmarks. \vspace{1mm} \item Implemented \textbf{CI/CD pipeline} for \textbf{SaaS architecture}, developing dynamic and interactive user interfaces with \textbf{unit}, \textbf{integration}, and snapshot tests, achieving \textbf{92.4\%}, enabling DevOps-driven zero-downtime staging deployments. \vspace{1mm} \item Utilized AngularJS and ReactJS for developing dynamic and interactive user interfaces with \textbf{unit}, \textbf{integration}, and snapshot tests, achieving \textbf{92.4\%}. \vspace{1mm} \item Maintained deep system \textbf{observability} via \textbf{tracing}, centralized logs, metrics across distributed runtime environments. \vspace{1mm} \item Containerized compute-intensive workloads using \textbf{Kubernetes}, enabling horizontal scaling across \textbf{10 node} clusters. \end{itemize} \vspace{5mm} \textbf{Full Stack Developer} \location{Mar 2020 -- Sept 2021} \\ \textit{Tanishq \& ProwessIQ Private Limited} \hfill \textit{} \\ \begin{itemize} \item Implemented \textbf{authentication mechanisms} with \textbf{OAuth2 and JWT}, enabling secure API communication and role-based access control, reducing unauthorized access attempts by \textbf{30\%} and ensuring compliance with enterprise security. \vspace{1mm} \item Designed and deployed an \textbf{AWS architecture} using EC2, S3, and \textbf{IAM roles}, streamlining secure cross-service communication and improving data availability and scalability, supporting workloads for \textbf{10K+} daily API requests. \vspace{1mm} \item Orchestrated \textbf{Infrastructure as Code (IaC)} with \textbf{Terraform}, automating provisioning pipelines and achieving \textbf{100\%} reproducible, version-controlled deployments, reducing manual configuration effort by \textbf{40\%} and deployment time by \textbf{60\%}. \end{itemize} \vspace{3mm} \section*{Projects} \begin{minipage}[t]{\textwidth} \textbf{EKS - Knowledge distilation} \textbar\ \textit{PyTorch, FSDP, DL Methods} \hfill \href{}{Stealth} \end{minipage} \begin{itemize} \item Developed a knowledge distillation pipeline for the \textbf{GPT-OSS} model using \textbf{Qwen-3 1.5B}, enabling efficient model inference by implementing custom loss functions at the PyTorch layer. \vspace{1mm} \item Architected and configured \textbf{GPU clusters} using \textbf{A100 nodes} and automated resource orchestration with \textbf{Kubernetes} and \textbf{Slurm}, enabling large-scale \textbf{knowledge distillation workloads} and efficient distributed training. \end{itemize} \vspace{3mm} \begin{minipage}[t]{\textwidth} \textbf{Shoplifting Detection using LSTM \& Yolov11} \textbar\ \textit{PyTorch, FSDP, DL Methods, NVIDIA Nsight} \hfill \href{}{Stealth} \end{minipage} \begin{itemize} \item Processed raw \textbf{CCTV video streams} into annotated frames, engineered temporal features, and trained a hybrid \textbf{Yolov11 \& LSTM} pipeline with \textbf{FSDP} for distributed training, enabling accurate spatio-temporal behavior detection. \vspace{1mm} \item Deployed the trained model on \textbf{GPU-backed inference servers}, integrating real-time video ingestion, \textbf{Redis}-based caching for frame-level prefetching, and a REST API, achieving sub-\textbf{200ms} detection latency in live retail environments. \end{itemize} \vspace{3mm} \begin{minipage}[t]{\textwidth} \textbf{Fraud Folio} \textbar\ \textit{AI, Fraud Detection, Meta Llama 3} \hfill \href{https://github.com/abinesha312/hack_unt_financial_fraud.git}{\faExternalLink} \end{minipage} \begin{itemize} \item Engineered a \textbf{custom fraud detection pipeline}, utilizing \textbf{Meta Llama 3} with \textbf{LLVM compiler optimization} for CUDA for HPC kernels, boosting real-time processing and anomaly detection accuracy. \end{itemize} \vspace{3mm} \begin{minipage}[t]{\textwidth} \textbf{Hybrid Vision Transformer for Small-Scale Image Classification} \textbar\ \textit{PyTorch, Transformers, MixUp, CutMix} \hfill \href{https://github.com/abinesha312/vision-transformer-cifar}{\faExternalLink} \end{minipage} \begin{itemize} \item Developed a \textbf{Hybrid Vision Transformer}, combining \textbf{CNNs} and \textbf{transformers} for CIFAR-10 classification, achieving improved feature extraction and interpretability through attention visualization. \end{itemize} \vspace{3mm} \begin{minipage}[t]{\textwidth} \textbf{TalentProbe: AI-Powered Interview Simulation Platform} \textbar\ \textit{GPT, FAISS, Flask, React, Whisper, RunPod} \hfill \href{https://talent-probe.vercel.app/}{\faExternalLink} \end{minipage} \begin{itemize} \item Built a \textbf{real-time interview practice app} with \textbf{Pandas}, \textbf{computer vision}, and \textbf{OpenAI}; integrated \textbf{FAISS} for rapid similarity search and \textbf{Whisper ASR} for voice analysis, enabling dynamic feedback on confidence and tone. \end{itemize} \vspace{3mm} \begin{minipage}[t]{\textwidth} \textbf{TeamBinary - Personality Prediction} \textbar\ \textit{PyTorch, DL Methods} \hfill \href{https://github.com/abinesha312/TeamBinary02}{\faExternalLink} \end{minipage} \begin{itemize} \item Built a \textbf{sentiment analysis model} using \textbf{MBTI-labeled data} with \textbf{XGBoost} to predict personality traits. \end{itemize} \section*{Education} \vspace{3mm} \textbf{Master of Science in Computer Science} \location{Aug. 2023 -- 2025} \\ \textit{University of North Texas} \hfill \textit{} \\ Relevant Courses: Machine Learning, Algorithms, AI Software Development, Information Retrieval, Big Data and Data Science \vspace{1mm} \textbf{Bachelor of Engineering in Information Science and Engineering} \location{May. 2021} \\ \textit{Panimalar Engineering college Affiliated to Anna University} \hfill \textit{} \\ Relevant Courses: Operating Systems, Data Structures, DBMS, Computer Networks, Object Oriented Concepts, deep learning \section*{Technical Skills} \vspace{3mm} \begin{itemize} \item \textbf{Programming Languages:} Python, C++, JavaScript, TypeScript, Bash, PowerShell, Shell Scripting. \item \textbf{JavaScript Frameworks:} Angular, React.js, Vue, Redux, Node.js, Express.js, Socket.IO, Micro-Frontend Architecture \item \textbf{Back-End Technologies:} FastAPI, Flask, Django, gRPC, RabbitMQ \item \textbf{Python Libraries:} Pandas, NumPy, Scikit-learn, TensorFlow, Keras, PyTorch, Matplotlib, Seaborn, Plotly \item \textbf{Deep Learning \& Distributed Training:} PyTorch (FSDP, DDP), HuggingFace Transformers, ONNX, LangChain, OpenAI, LLama-Stack, LLama Models. \item \textbf{Databases:} Redis, MongoDB (NoSQL), DynamoDB, Postgres, Databricks, MySQL \item \textbf{Cloud \& DevOps:} AWS (Lambda, API Gateway, Step Functions, DynamoDB, S3, RDS, ECS, EKS, SageMaker, Transcribe, Polly, CDK), Docker, Terraform \end{itemize} \vspace{1mm} \end{document} ```