Senior ML Engineer, LLM Infrastructure

Nikhil is an ML Engineer with 8 years of experience building production AI systems, specializing in LLM infrastructure, search/retrieval, and applied ML. Most recently, as Lead Data Scientist at Eka.care, he deployed a Speech LLM (Whisper + Gemma 2) via custom vLLM plugins, cutting inference costs by 60%. He built medical search on ElasticSearch, improving nDCG@10 by 55% and relevance by 160%. Nikhil designed MedAssist, an agentic LLM platform adopted by Apollo Hospitals, and open-sourced KARMA, an LLM evaluation library for Indian healthcare. He architected model serving on Kubernetes (vLLM, RayServe, TensorRT), reducing costs by 50% compared to SageMaker. His prior experience includes search ranking at Udaan, research at NCBS-TIFR (published in Bioinformatics), and clinical AI at SigTuple (retinal disease detection through CE certification). He has 3 peer-reviewed papers and recently completed Stanford CS336 (LLMs from scratch) with distributed training on H100 clusters. He is looking for Senior/Staff ML Engineer, Applied Scientist, or AI Engineer roles, with a preference for remote work but willing to relocate anywhere in Germany or the EU.