Summary
Maheep Kumar is a Senior Software Engineer with 9 years of experience building production-grade distributed systems and GenAI infrastructure, currently driving large-scale LLM serving and ML platform work at HG Insights. He designs high-throughput services and pipelines—think 1B+ requests/day at low-ms latencies—and has deployed LLM inference on NVIDIA H100 clusters handling 800M+ monthly calls. His work spans ML-powered caching, vector search, agentic workflows, and developer platforms, delivering measurable business impact like a lift in data fill rates from 45% to 83%, an 85% reduction in API calls, and multimillion-record processing pipelines. Maheep blends systems engineering rigor with pragmatic architecture choices, routinely cutting costs (e.g., $24k/month saved) while improving conversion and developer velocity via gRPC migrations. Comfortable in Python, Go, Rust, Elixir and cloud-native stacks, he also tinkers with automation, Apple apps and robots in his spare time—an indicator of hands-on curiosity that fuels his production-focused innovations. Based in Pune, he pairs a Thapar University CS background with a steady track record of turning complex ML and distributed challenges into reliable, operational systems.
9 years of coding experience
4 years of employment as a software developer
Bachelor’s Degree, Computer Science, Bachelor’s Degree, Computer Science at Thapar University
English, Hindi, Punjabi, Japanese