Rohil Gupta is a Lead ML Infrastructure Engineer with 8 years of experience building production-grade MLOps, NLP, and LLM/ASR systems for cloud-native environments. He bridges research and production, delivering measurable efficiency gains—automating GPU scaling to cut nighttime costs by ~40%, and leading a batched ASR redesign that achieved 18x lower latency and 128x higher throughput. Rohil architects scalable, secure platforms (Helm-based deployments, stateless LLM-Guard moderation) and builds observability tooling, including a production Python telemetry library integrated with VictoriaMetrics and Grafana. His background in healthcare NLP and genomics informs practical, compliant deployments, while his hands-on benchmarking of H100/H200 GPUs and optimization of JSON generation for OSS LLMs show a knack for low-level performance tuning. Based in Lyon, he combines data-science instincts with DevOps rigor to turn complex AI workflows into reliable, cost-efficient services.
Contributions:17 commits, 2 pushes, 2 branches in 1 day
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.