Senior AI Deployment & Inference Engineer
Posted Updated
Description
CoreWeave is seeking a Senior Deployment Engineer to bring AI models into production, optimize performance, and integrate with enterprise systems. You will own technical delivery from discovery to adoption, working closely with customers and product/engineering teams.
Ideal candidates have 5+ years of hands-on experience in software/ML engineering, strong Python and ML framework skills, and expertise in deploying LLMs with model-serving tools. Excellent communication to customers is essential.
Lead technical discovery to define use cases, workloads, and targets for model quality and latency. Optimize inference using quantization, batching, caching, and parallelism. Adapt models via prompt optimization, retrieval-augmented generation, and fine-tuning. Troubleshoot performance across model execution, GPU, memory, and serving infra. Lead technical customer engagements, run benchmarks, and guide deployment decisions. Build reusable deployment configurations, evaluation tools, and runbooks. 5+ years in software/ML engineering or related hands-on role. Strong Python and ML framework skills (PyTorch, Transformers). Hands-on experience deploying and optimizing AI models in production (LLMs). Experience with model-serving frameworks (vLLM, TensorRT-LLM). Understanding GPU memory constraints, precision, batching, caching, and parallelism. Medical, dental, vision insurance Life Insurance Retirement plan Tuition Reimbursement Employee Stock Purchase Program Paid parental leave Flexible PTO Catered lunchSkills
Sign in to read and join the discussion.