Headline

Building RAG Systems & LLM Pipelines | Open to AI Engineer & MLOps Roles

About

I build AI systems optimized for speed, accuracy, and scale. No fluff, just high-grade engineering. ​The Metrics: ​Speed: Optimized a RAG eligibility checker (Groq + Pinecone + FastAPI) down to <800ms end-to-end latency. ​Reliability: Fine-tuned a BERT hallucination detector to 94.6% accuracy on a 50k-sample dataset. ​Scale: Containerized and deployed APIs to GCP Cloud Run, built to sustain 500+ concurrent requests. ​Impact: Reduced support tickets by 35% at Pratinik Infotech by building an NLP chatbot. ​Actively looking for full-time AI Engineer or ML Engineer roles where I can own pipelines, optimize infrastructure, and ship things that actually work under real traffic. ​📬 sinamchayan@gmail.com

Location

Navi Mumbai

Work experience

Artificial Intelligence Engineer Intern at PRATINIK INFOTECH, Aug 2024 - Oct 2024 · 3 mos, Engineered and trained classification models to categorize student queries, achieving 92% accuracy in intent detection. Built an NLP-based chatbot integration that resolved common student issues automatically, resulting in a 35% reduction in manual support tickets. Managed the end-to-end data pipeline over an 8-week tenure, including text cleaning and processing using Pandas and NumPy.

Contingent Leader at Mood Indigo IIT Bombay, Jan 2023 - Apr 2024 · 1 yr 4 mos, Mumbai, Maharashtra, India

Education

B.Tech CSE (AI&ML), Chhatrapati Shivaji Maharaj University, Panvel

CBSE Class 12, PCM, Shree Dalauda Public School