Yash Singhal — AI Researcher

AI Engineer and final-year CS student. I build production LLM systems that ship. Currently interning at Researchwire Knowledge Solutions. I work on RAG pipelines for large-scale patent analysis, processing 1M+ documents with sub-second semantic search. I improved retrieval precision by 40% and reduced system latency by 30-40%. I cut unnecessary LLM calls by 50% and achieved 2-3x inference throughput improvement by deploying vLLM with hybrid ML strategies. Other highlights: IEEE-published researcher. Developed a Random Forest model (R2 = 0.54) for rainfall prediction, presented at IC3-2025. Delivered 10+ freelance AI applications for clients on AWS, Azure, and GCP. Authored 20+ technical articles read by 5,000+ developers. Built a multilingual RAG chatbot for 10+ languages with sub-500ms transcription latency. Deployed full MLOps pipelines on Kubernetes using Jenkins and ArgoCD, cutting release time to under 8 minutes. I take full ownership of every project. From system design and prompt engineering to Docker, Kubernetes, monitoring, and production optimization. I thrive in fast-moving environments where I can build and ship real things. Open to AI Engineer, Generative AI Engineer, and Full-Stack Engineer roles from mid-2026. Reach me at: yashsinghal9886@gmail.com Skills: RAG, LangChain, LangGraph, Multi-Agent Systems, vLLM, LLM Fine-tuning, PyTorch, Prompt Engineering, Pydantic, OpenAI API, Qdrant, Docker, Kubernetes, Jenkins, ArgoCD, CI/CD, Terraform, AWS, Azure, GCP, FastAPI, Next.js, React.js, Python, TypeScript, System Design, Data Pipelines, Technical Writing

Stackforce AI infers this person is a SaaS-focused AI Engineer with strong full-stack and MLOps expertise.

Location: Delhi, India

Experience: 5 mos