Reval LogoFind More Talent
US

Utkarsh Srivastava

Junior Machine Learning Engineer specializing in LLMs, RAG, and medical imaging

New York City, USAMachine Learning Researcher, Non Traditional Volunteer3 years experienceJuniorHealthcareHealthcare ITLegal
ScreenedIdentity Verified

Connect with Utkarsh

Utkarsh already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.

Recommended

Already have an account?

About

At Fileread, the candidate built and deployed an LLM-powered legal document classification and retrieval layer for an agentic extraction system that turns unstructured legal PDFs into structured tables with line-level citations. They productionized a RAG-style pipeline (ingestion, embeddings, retrieval, reranking, generation) and report 95%+ F1 across 70+ legal categories, emphasizing rigorous evaluation and close collaboration with legal domain experts for high-stakes precision.

Experience

Machine Learning Researcher, Non Traditional VolunteerNYU Langone Health
Machine Learning Engineer InternFileread AI
Visting Researcher, JUACEP Fellowship awardeeFujii Lab, Nagoya University
Research AssistantSikkim Manipal Institute of Technology

Education

New York Universitymaster, Computer Engineering (2025)
Sikkim Manipal Universitybachelor, Computer Science and Engineering (Hons. AI) (2023)

Key Strengths

  • Built and productionized LLM-powered legal document classification/retrieval pipeline
  • Achieved 95%+ F1 across 70+ legal categories on a large labeled dataset
  • Designed agentic extraction system converting legal PDFs into structured tables with line-level citations
  • Structured prompt iteration using constrained templates and fixed evaluation query sets
  • Reliability-focused agent design with explicit, observable workflow steps
  • Evaluation-driven approach using grounding accuracy, citation precision, latency, and fallback rates
  • Pragmatic model/retrieval selection: start with baselines and add complexity (e.g., reranking/structured prompts) based on measured failure modes
  • Effective cross-functional collaboration with legal domain experts to define success criteria and acceptable failure cases

Discover more candidates like Utkarsh

Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.

Search Talent

Connect with Utkarsh

Utkarsh already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.

Recommended

Already have an account?

Contact

candidate@example.com(555) 123-4567LinkedIn Profile
Sign up to view

Languages

English

Skills

Large Language Models (LLMs)Retrieval-Augmented Generation (RAG)AI AgentsAgentic extractionOpenAI APIEmbeddingsPrompt engineeringDense retrievalBM25Hybrid searchRerankersVector databasespgvectorFAISSInformation retrieval