jobs
Research Engineer, Post-Training Inference
About the role The Model Shaping team at Together AI works on products and research focused on tailoring open foundation models to downstream applications.
In inglese
- Company
- Together AI
- Location
- San Francisco
- Status
- Closed
- Posted
- 2026-07-06 18:21 UTC
Together AI's Model Shaping team tailors open foundation models to downstream applications. The research engineer will build the platform that lets developers customize open-source models with their own data, wiring fine-tuning, reinforcement learning and evaluation services into the inference stack, optimizing engines for RL workloads, and joining an on-call rotation. The posting asks for 2+ years deploying ML services in production, hands-on work with SGLang, vLLM or TensorRT-LLM, familiarity with current fine-tuning methods, and Python or Go. Multi-LoRA serving, low-precision kernels, Triton/CUDA work and Kubernetes experience stand out.
Original job posting