Farshad Ghodsian

Senior AI Engineer - Accelerated Computing

Toronto, Ontario, Canada
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Farshad Ghodsian is a Senior AI Engineer focused on accelerated computing with seven years of experience building large-scale ML, MLOps and Generative AI platforms. He blends hands-on engineering and product strategy from roles at NVIDIA and AMD to design AI cluster management, Kubernetes-based deployments, and high-performance inference/training solutions. Previously he led enterprise GenAI and RAG platform projects across AWS, Azure and GCP, delivering secure, production-ready pipelines, microservices for PII detection, and safety guardrails for assistant chats. Comfortable moving between developer docs, demos and pre-sales, he’s equally at home mentoring teams and authoring technical content to help customers adopt ROCm and AI infrastructure. Based in Toronto, he brings systems architecture and cloud-native pragmatism to bridge research-grade models with operational data center deployments—often surfacing operational needs that accelerate product roadmaps.
code7 years of coding experience
job1 year of employment as a software developer
bookMajored in Biology, Majored in Biology at York University
bookGraphic Design, Graphic Design at International Academy of Design & Technology-Toronto
github-logo-circle

Github Skills (46)

pytorch10
runtimes10
tensorrt10
kubeflow10
nvidia10
cuda10
cpp10
llm9
python9
large-language-models9
inference9
neural-architecture-search9
quantization9
gpt8
go8

Programming languages (5)

DockerfileC++GoYAMLPython

Github contributions (5)

github-logo-circle
Contributions:40 pushes, 19 branches in 6 months
A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed.
Contributions:24 pushes in 12 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.
Request Free Trial