Aaqib Ansari is an IT Analyst with over 11 years of experience specializing in QA, DevOps and MLOps for cloud-native and AI deployments. He has driven testing and automation initiatives across enterprises like Capgemini and TCS, led QA teams, and contributed backend and performance work to notable open-source projects such as AWS Multi-Model-Server, PyTorch Serve, and SageMaker examples integrating NVIDIA Triton. Comfortable across the stack, he blends hands-on test automation, benchmark tuning, and model-serving infrastructure to help move ML models from prototype to production. Based in Lucknow, he pairs an MCA background with practical engineering chops and a knack for refining test and deployment pipelines that improve reliability and scalability. An interesting facet: beyond QA leadership he’s actively contributed to container and inference-server tooling used by large ML teams, reflecting both breadth and a production-first mindset.
11 years of coding experience
6 years of employment as a software developer
BCA, Computer Programming, BCA, Computer Programming at SHIATS-Allahabad
Std11-std12, PCMH, Std11-std12, PCMH at Mary Lucas School And college
MCA, Computers, MCA, Computers at LOVELY PROFESSIONAL UNIVERSITY
6std-10std(Boards), I had done my schooling foundation from Unity Public School and choosen Science Stream in Boards., 6std-10std(Boards), I had done my schooling foundation from Unity Public School and choosen Science Stream in Boards. at Unity Public School, Allahabad
Serve, optimize and scale PyTorch models in production
Role in this project:
DevOps Engineer
Contributions:3 releases, 427 reviews, 194 commits in 2 years 8 months
Contributions summary:Aaqib's commits focused on modifying benchmark scripts and configuration files to improve performance testing capabilities. They updated the benchmark script to include GPU usage, specified docker runtime, and defined model download URLs. The changes also involved modifying the configuration for different test runs, enabling S3 upload for metrics, and generating reports. These actions aimed to refine and optimize the benchmarking process for the PyTorch Serve repository.
Multi Model Server is a tool for serving neural net models for inference
Role in this project:
Backend Developer
Contributions:7 releases, 10 reviews, 11 commits in 1 year 8 months
Contributions summary:Aaqib primarily focused on backend code modifications and improvements within the multi-model-server repository. Their contributions include cleaning up resources related to worker threads, implementing IO stream handling, and refactoring code related to server thread management and shutdown. They also made version updates and documentation changes to the project.
pytorchmxnetservingdeep-learninginference
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.
Request Free Trial
Aaqib Ansari - IT Analyst at Tata Consultancy Services