.png){kind=logo}
Shreya Thakur
Mid-level Software Engineer specializing in Python backend and LLM/ML systems
Connect with Shreya
Shreya 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
Backend/AI engineer who has shipped production LLM systems end-to-end, including an AI request-routing service (FastAPI + BART MNLI + OpenAI/Gemini) that improved accuracy ~25% after launch via eval-driven prompt/category iteration. Also built an enterprise document intelligence/RAG platform on Azure (Blob/SharePoint/Teams ingestion, OCR/NLP chunking, embeddings in Azure Cognitive Search) with PII guardrails (Presidio), confidence gating, and scalable event-driven pipelines handling millions of documents.
Experience
Education
Key Strengths
- Shipped end-to-end LLM request routing system (zero-shot classification + multi-LLM integration)
- Improved routing accuracy ~25% through prompt/category refinement and expanded eval dataset
- Built production RAG document intelligence system on Azure (ingestion → embeddings → retrieval → generation)
- Implemented strong privacy guardrails (PII detection/masking + approval workflow) to prevent sensitive data exposure
- Designed reliability controls for LLM apps (confidence thresholds, retrieval gating, fallback responses)
- Scaled ingestion and indexing pipeline to millions of documents using event-driven processing, batching, and embedding caching
- Established evaluation loops with labeled test sets, human review, and regression prevention
Discover more candidates like Shreya
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent