AnweshSatapathy
Summary
👤
SeniorAnwesh Satapathy is a Machine Learning Engineer with a decade of experience building production-grade ML and backend systems, currently optimizing inference at Snap in San Francisco. He has engineered end-to-end LLM solutions (RAG, LoRA/QLoRA, AWQ), scalable microservices, and real-time vLLM inference stacks that delivered multi-fold throughput improvements and sub-second latency gains. Previously at Dell he drove NLP pipelines, Kafka streaming, and resilient CI/CD that supported 10M+ device tracking and cut operational effort by 90%. Comfortable across distributed training (FSDP, DeepSpeed), large-scale data pipelines (Spark, Hive), and observability (Prometheus/Grafana), he combines research-caliber rigor (ASU MS, 4.0 GPA) with practical production reliability. Notably, he blends deep model tuning with backend engineering to squeeze latency and cost from inference—not just accuracy—making models cheaper and faster in real-world systems.
10 years of coding experience
Github Skills (17)
deeplearning-ai10
kubernetes9
python9
machine-learning9
deep-learning9
fastai9
cuda8
ai8
inference8
amd8
pytorch8
llm7
openai7
llama7
transformer7
Programming languages (4)
Github contributions (5)
AI6-Bangalore-Chapter/2018-cycle-2
Aug 2018 - Feb 2019
Contents covered in sessions of AI Saturdays (cycle 2) as well as relevant material for further study.
Contributions:86 commits, 78 pushes, 1 branch in 6 months
aideep-learningmachine-learningfastaideeplearning-ai
Anwesh2/anwesh2.github.io
Feb 2018 - Feb 2018
Contributions:124 pushes, 1 branch in 2 days
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.