Swapnesh Khare is a Staff ML Engineer with 12 years of experience building and operationalizing machine learning systems across finance, insurance, and commodities. He specializes in end-to-end ML platforms—migrating realtime APIs to GKE, deploying 40+ DS workloads, and serving 45+ deep learning models via Triton to achieve significant GPU cost savings. Swapnesh has led data platform initiatives (feature store with Feast, inference and request stores, Pub/Sub/Kafka pipelines, Medallion data tiering) and driven >60% cost reductions through engineering and storage optimizations. Comfortable across data engineering, model optimization (TensorRT, HuggingFace Whisper), and infra (Airflow, Starrocks, Trino), he prefers the title ML Engineer because he blends infrastructure, deployment, and product-focused modeling. Based in Gurugram, he’s known for pragmatic automation—e.g., converting Detectron2 to TensorRT and building an ML Gateway—that turns experimental models into reliable production services.
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.