About the Role
Together AI is looking for an ML Engineer who will develop systems and APIs that enable our customers to perform inference and fine tune LLMs. Relevant experience includes implementing runtime systems that perform inference at scale using AI/ML models from simple models up to the largest LLMs.
Responsibilities
- Design and build the production systems that power the Together Cloud inference and fine-tuning APIs, enabling reliability and performance at scale
- Partner with researchers, engineers, product managers, and designers to bring new features and research capabilities to the world
- Analyze and improve efficiency, scalability, and stability of various system resources
- Conduct design and code reviews
- Create services, tools & developer documentation
- Create testing frameworks for robustness and fault-tolerance
- Participate in an on-call rotation to respond to critical incidents as needed
Requirements
- 5+ years experience writing high-performance, well-tested, production quality code
- Bachelor’s degree in computer science or equivalent industry experience
- Familiar with LLM inference ecosystem, including frameworks and engines (e.g. vLLM, SGLang, TRT, ...)
- Demonstrated experience in building large scale, fault tolerant, distributed systems like storage, search, and computation
- Expert level programmer in one or more of Python, Go, Rust, or C/C++
- Experience implementing runtime inference services at scale or similar