Gavrish Prabhu
Member Of Technical Staff at Nutanix
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolGavrish Prabhu is a Member of Technical Staff with three years of experience building cloud-native, scalable systems from Bengaluru. He has driven performance and cost optimizations at Citrix—accelerating upload/download throughput by 30%, reducing COGS by millions, and scaling an AV scanning pipeline to handle 15M files/day within tight SLAs—before moving to Nutanix. Gavrish blends backend engineering, distributed systems and MLOps expertise, contributing to KServe by integrating vLLM support for large language model inference on Kubernetes and improving Hugging Face server integration. Comfortable across AWS services, CI/CD modernization and encryption for petabyte-scale data, he pairs pragmatic engineering with measurable business impact. Colleagues describe him as someone who “builds value wherever you are,” combining hands-on execution with a knack for reliable, production-ready integrations.
3 years of coding experience
4 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at PES UniversityCanara High SchoolCanara Pre University College
English, Kannada, Hindi, Sanskrit, Tulu, Konkani
Github Skills (10)
huggingface-transformers10
kubernetes10
machine-learning10
mlops10
python10
kubernetes-pods10
llm10
openai-api9
docker8
dockers8
Programming languages (4)
Github contributions (5)
kserve/kserve
Feb 2023 - Mar 2025
Standardized Serverless ML Inference Platform on Kubernetes
Role in this project:
MLOps Engineer
MLOps EngineerContributions:74 reviews, 17 PRs, 134 comments in 2 years 1 month
Contributions summary:Gavrish primarily contributed to integrating and enhancing vLLM support within the KServe platform, a standardized ML inference platform on Kubernetes. Their work involved implementing vLLM as an alternative backend for serving large language models, addressing issues related to parallelism, and incorporating features for OpenAI completions. The contributions included refactoring code, fixing build failures, and optimizing the integration of vLLM with the existing Hugging Face server components.
xgboostsklearnserverlessclient-goknative
gavrissh/kserve
Jan 2024 - Mar 2025
Standardized Serverless ML Inference Platform on Kubernetes
Contributions:185 pushes, 17 branches in 1 year 3 months
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.