Generative AI Engineer
Lokesh Chimakurthi
Building intelligent systems that understand context. Specializing in RAG architectures, AI agents, and context engineering for production-scale applications.
Scroll
Building intelligent systems that understand context. Specializing in RAG architectures, AI agents, and context engineering for production-scale applications.
I'm a Generative AI Engineer with a passion for building systems that truly understand context. My work focuses on the intersection of retrieval systems, language models, and agentic architectures—creating AI that doesn't just respond, but reasons.
Currently at Eka Care, I architect Text-to-SQL agents and MCP servers that transform how enterprises interact with their data. I'm driven by the belief that the best AI experiences feel less like technology and more like conversation.
When I'm not engineering context windows, you'll find me contributing to the open-source AI community. My ModernPubMedBERT model trends on HuggingFace with 1,000+ monthly downloads, pushing the boundaries of biomedical NLP.
Hybrid RAG system engineered for reliable, context-aware answers from complex document types. Multi-stage retrieval pipeline with semantic double merging chunking.
State-of-the-art sentence-transformer fine-tuned on PubMed abstracts and clinical data. Trending on HuggingFace, outperforming competing models on BEIR benchmarks.
Most RAG tutorials stop at 'chunk your docs and query.' Real production systems need hybrid retrieval, re-ranking, semantic caching, and graceful fallbacks. Here's the architecture I use to build RAG pipelines that actually work at scale.
Read MorePrompt engineering is dead. The real leverage is in what you feed the model before the prompt—system instructions, retrieved documents, conversation history, tool outputs. Here's how to think about context as a first-class engineering problem.
Read MoreWhen I trained ModernPubMedBERT, generic embedding models failed on medical terminology. This post covers the full pipeline: curating contrastive pairs, choosing loss functions, avoiding catastrophic forgetting, and benchmarking.
Read MoreInterested in AI agents, RAG systems, or context engineering? I'm always open to discussing new opportunities and ideas.
lokeshchimakurthi19@gmail.com