Member of Technical Staff, Forward Deployed Engineer

Inferact seeks a Forward Deployed Engineer to work directly with customers deploying and optimizing vLLM inference systems. This hands-on role involves architecture discussions, implementation, debugging, and turning field learnings into product capabilities. Requires strong software engineering, ML systems experience, and systems debugging skills.

Minimum: Bachelor's in CS/engineering or equivalent, strong software engineering in Python/Go/TypeScript, hands-on ML systems deployment, ability to work with customer teams, systems debugging skills, reasoning about latency/throughput/scaling. Preferred: experience with vLLM, SGLang, TensorRT-LLM, GPUs, CUDA/ROCm, enterprise deployments, building APIs/CLIs, profiling performance.