Member of Technical Staff, Developer Relations
Core
Developer Relations Engineer focused on educating developers and building public artifacts (tutorials, demos, docs) for vLLM, an open-source LLM inference engine.
Role type
Senior IC Developer Relations Engineer (Inference Systems)
Builds
Public technical artifacts including blogs, tutorials, workshops, demos, and documentation for vLLM and adjacent inference systems.
Domain
AI Infrastructure / LLM Inference Systems
Deliverable
product features
Required skills
LLM inference systems, model serving, GPU inference, distributed runtimes, scheduling, batching, quantization, KV cache, PagedAttention, continuous batching, prefill/decode scheduling, prefix caching, speculative decoding, tensor parallelism, data parallelism, latency vs throughput tradeoffs
Preferred skills
ML systems, distributed systems, HPC, compilers, GPU kernels, serving infrastructure, MLOps, developer tooling, open-source infrastructure, CUDA, Ray, PyTorch, Modal, BentoML, Baseten, Predibase, Together AI, Anyscale, LMSYS
Technologies
vLLM, SGLang, TensorRT-LLM, TGI, LoRAX, Ray Serve, FlashInfer, BentoML, Baseten (via careerplan.io/jobs/e1a91db5-1cd4-4688-863b-33ab88b40a4d-member-of-technical-staff-developer-relations-at-inferact)
Responsibilities
Write technical deep dives, build demos, create tutorials, contribute to docs and examples, host workshops, explain complex inference concepts to practitioners
Seniority
Senior, hands-on IC
