About this role
Research Engineer, Post-Training Inference at Together AI. Location: San Francisco, California, United States. Role: designing systems, building integrations, optimizing inference Requirements: 2+ years building/deploying ML services; experience with inference engines (SGLang, vLLM, TensorRT-LLM); familiarity with fine-tuning LLMs; strong software engineering in Python or Go; on-call participation. Category: Research and Development (R&D) Seniority: Entry Level Tools: SGLang, vLLM, TensorRT-LLM, Python, Go, CUDA, Triton, CuTE, Kubernetes, FlashAttention, ATLAS, RedPajama, Mamba Commitment: Full Time Workplace: Onsite Languages: English