Machine Learning Engineer - Inference
Together AISan Francisco, California, United States
Posted August 12, 2025
160000 - 230000 USD year
Full Time
About the Company
Together AI is a research-driven AI cloud infrastructure provider offering a purpose-built GPU platform for training and running advanced AI models. Serving leading SaaS companies and pioneering startups, Together AI champions open source AI and decentralized computing, advocating for transparency to drive innovation and societal benefits.
Job Description
Together AI is seeking a Machine Learning Engineer to optimize performance of their AI inference systems using state-of-the-art large language models. The role involves designing and building production systems, collaborating with researchers, and developing cutting-edge AI solutions. It offers the chance to work with AI researchers and engineers on projects shaping the future of AI.
Requirements
- 3+ years of experience writing high-performance, well-tested, production-quality code.
- Proficiency with Python and PyTorch.
- Demonstrated experience in building high performance libraries and tooling.
- Excellent understanding of low-level operating systems concepts.
- Experience with AI inference systems like TGI, vLLM, TensorRT-LLM, Optimum (preferred).
Benefits
- competitive compensation
- startup equity
- health insurance
