Alpay Ariyak
AI Research Scientist at Together AI
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAlpay Ariyak is a Staff Research Scientist at TogetherAI with four years of hands-on experience advancing post-training for LLMs and coding agents, currently leading efforts on overall intelligence and reasoning. He shipped state-of-the-art coding models (SWE Agent, DeepSWE, CoderForge-Preview, DeepCoder) and co-led the OpenChat workstream, blending research rigor with production-focused engineering. Previously he built serverless inference and post-training infrastructure at RunPod and trained multi-modal math models at EdLight, showing a rare mix of systems and model expertise. Based in San Francisco, he moves smoothly between experimental RL/NLP research and scalable deployment, and has a background at Worcester Polytechnic Institute including graduate research—hinting at a strong foundation in both theory and applied ML.
4 years of coding experience
2 years of employment as a software developer
Bachelor of Science - BS Computer Science, Bachelor of Science - BS Computer Science at Worcester Polytechnic Institute
Turkish, English, Russian
Github Skills (43)
pytorch10
llama10
inference10
tpu10
amd10
llm10
mlops10
llmops10
xpu10
cuda10
transformer10
gpt10
bert-embeddings10
docker9
api9
Programming languages (4)
Github contributions (5)
runpod-workers/worker-vllm
Sep 2023 - Jul 2024
The RunPod worker template for serving our large language model endpoints. Powered by vLLM.
Contributions:10 releases, 25 PRs, 186 pushes in 10 months
language-modelllmrunpodvllm
alpayariyak/MRF-RL
May 2022 - Nov 2022
Contributions:83 commits, 65 pushes, 16 branches in 5 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.