Adesh Swapnil is a Python AI/LLM developer with 11 years of engineering experience and 6+ years focused on building production-grade ML and GenAI systems in cloud-native environments. He designs and deploys scalable RAG pipelines, fine-tunes domain LLMs with LoRA/QLoRA, and ships inference endpoints optimized for cost and latency using SageMaker, TGI, and Ray Serve. Comfortable across the ML lifecycle, he automates MLOps with MLflow/W&B/ZenML, orchestrates features and real-time pipelines with Kafka, Airflow, Feast, and Snowflake, and serves models via FastAPI and Kubernetes. His work spans vector databases (Pinecone, FAISS, Weaviate), multi-modal models (CLIP, Whisper, BLIP), and tool-augmented agents using LangChain, LangGraph, and Haystack. At Morse and Pax8 he translated research into measurable production impact—automating ticket triage, reducing inference costs, and improving latency—while also contributing to internal AI research on agentic workflows and LLM distillation. Based in New York and shipping at VapiAI, he blends deep ML engineering with pragmatic product delivery and a knack for squeezing performance and cost out of large-model deployments.
Contributions:8 releases, 78 pushes, 5 branches in 1 year 6 months
androidandroid-appkotlinfrcscouting
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.