About this role
Staff/Principal Forward Deployed Engineer at DiDi Labs. Location: San Jose or Mountain View. Role: designing architecture, deploying models, optimizing infrastructure Requirements: Expert in LLMs and AI platform architecture, distributed LLM training/inference, GPU cluster optimization; proficiency in C++, Python, Java, JavaScript; experience with PyTorch, Ray, vLLM, Triton, Kubernetes, DeepSpeed, Megatron-LM; senior-level engineering experience preferred. Category: Engineering Seniority: Senior Level Tools: Llama, Hugging Face, PyTorch, Ray, vLLM, Triton Inference Server, Kubernetes, DeepSpeed, Megatron-LM, C++, Python, Java, JavaScript Commitment: Full Time Workplace: Onsite Languages: English