~/sameer-batra

Experience

3+ years of AI/ML experience across industry and applied research.

Where I've worked

  1. George Washington University · LAiSER

    Jan 2025 – Present

    Research Specialist

    Leveraging AI for Skills Extraction & Research, a George Washington University initiative building open-source tools that extract and align skills from education and workforce data.

    • Architected the LAiSER knowledge graph, unifying 18K+ skills across ESCO, O*NET, UK Skills and OSN with 11.6K links. Grounding an LLM in the graph improved faithfulness from 0.65 to 0.83.
    • Built LAiSER 2.0, an agentic system on an MCP server that exposes skill, knowledge and task extraction as callable tools over a Neo4j graph, and skips the full agent cycle when a direct Cypher query is enough.
    • Fine-tuned a 2.7B Phi-2 model (SkillPhi-R) with LoRA and 4-bit quantization for skill extraction. It won the GWU open-source award.
    • Mentored five interns: three on the knowledge graph, two on an NLP paper about phantom vacancies, now in review. Cut collection of 100K+ syllabi from 31 Texas universities to three days with an EC2 scraper.
    • Shipped LAiSER as a Python package and API, with GitHub Actions tests gating every merge to main.
    Read the case study →
  2. FGS Global

    Jan 2026 – May 2026

    Data Science Fellow

    Global strategic communications firm.

    • Designed a tiered scoring system (DeBERTa-v3, XGBoost, GPT-4) to replace Perspective API, used daily by 10 analysts. It cut analyst review time by about 83%. Sending only the ambiguous 10–15% of cases to the costliest model cut inference cost by 85–90%.
    • Benchmarked four moderation APIs (Perspective, Azure Content Moderator, AWS Comprehend, OpenAI Moderation) to justify a custom build.
    • Applied ordinal regression on a 1–10 threat scale with behavioural features to suppress false positives, and designed pre-deployment test suites covering multilingual samples and coded threats.
    • Built a Neo4j knowledge graph mapping stakeholder influence across 50,000+ media records and ranked key audiences with centrality analysis.
  3. George Washington University

    Aug 2025 – Jan 2026

    Graduate Instructional Assistant

    • Supported Introduction to Data Mining for 30+ graduate students: ran sessions, wrote quizzes, graded assignments and designed hands-on exercises.
    • Coached students on how to present their final data mining and machine learning projects.
  4. Customs Declaration UK

    Jan 2023 – Jan 2025

    Junior Data Scientist

    Platform that helps users complete UK customs declarations.

    • As sole technical owner, built and deployed a production RAG system on Azure with Qdrant vector search that turned UK customs regulations into guidance. About 10,000 people used it, and form completion time fell by about 60%.
    • Gave plain-English guidance across thousands of commodity codes by grounding the assistant in vector-indexed regulations.

Education

  • George Washington University

    Master of Science in Data Science

    Jan 2025 – Present

  • SZABIST, Karachi

    Bachelor of Science in Computer Science

    Aug 2020 – May 2024

Toolbox

PythonSQLPyTorch / Hugging FaceLoRA / PEFTRAGNeo4jQdrantMCPClaude CodeDockerGitHub ActionsAWS (EC2, Lambda, Bedrock)Azure