Open to opportunities

Esa Sri E

@esasrie

Message

AI/ML and full-stack developer building reliable RAG systems.

India

Message

What I'm looking for

I’m looking for AI/ML or software engineering roles where I can evaluate LLM outputs for factual accuracy and reliability, improve RAG pipelines, and ship production features with strong engineering practices and fast feedback.

I’m a Computer Science graduate (2026) with hands-on experience in full-stack development and AI/ML systems. During my AI/ML internship, I built and deployed a production RAG chatbot using Gemini API, FAISS, and FastAPI, including LLM output evaluation for factual accuracy, relevance, and citation quality.

I take a structured, detail-oriented approach to improving reliability—refining prompts and retrieval strategies to improve accuracy by ~25%. I also built a ChatGPT-style streaming frontend with follow-up suggestions and feedback buttons, and I’ve supported data-driven work through Power BI dashboards and ML research (including preprocessing 5,000+ patient records with 87% classifier accuracy).

Experience

Work history, roles, and key accomplishments

AI/ML Intern - RAG Evaluation

AltruistyInnovation Pvt Ltd

Jan 2025 - Apr 2025 (3 months)

Evaluated LLM-generated responses for factual accuracy, relevance, and citation quality during RAG testing by cross-checking against trusted sources and comparing multiple variants. Built an end-to-end RAG pipeline (PDF/DOCX parsing, chunking, embeddings, FAISS indexing, semantic retrieval) and improved LLM accuracy by ~25%, while delivering a streaming chat frontend with follow-up suggestions and

RAG LLM Evaluation Prompt Engineering Faiss fastAPI Gemini API PDF Parsing Agile Scrum