Luma AI
Software Engineer, Inference
$195K–$345K
Redwood City, CA +3 · Hybrid · Full-time · Posted Oct 8, 2026
- Location
- Redwood City, CA
Remote, US
New York, NY
Seattle, WA
About the job
Build and operate large-scale model inference systems, integrating architectures and optimizing deployments, reliability, and GPU utilization.
What you'll do
- Integrate new model architectures into the inference engine and collaborate on model efficiency and deployments.
- Build tools and scheduling systems to measure inference workflows and optimize GPU workloads across clusters and hardware providers.
- Automate, test, and maintain reliable inference services and deployment pipelines, including CI/CD for model checkpoints and SDKs.
What they ask for
- Strong Python and system-architecture skills.
- Experience deploying models with PyTorch, Hugging Face, vLLM, SGLang, TensorRT-LLM, or similar.
- Experience with queues, scheduling, traffic control, and fleet management at scale.
- Experience with Linux, Docker, and Kubernetes; familiarity with Redis and S3-compatible storage.
Nice to have
- Modern networking stacks including RDMA (RoCE, InfiniBand, NVLink).
- High-performance large-scale ML systems (100+ GPUs), CUDA, and FFmpeg or multimedia processing.
Pay
$195K – $345K (base salary)
Tools
Python, PyTorch, Hugging Face, vLLM, SGLang, TensorRT-LLM, Linux, Docker
AI focus
Serve models in production by integrating architectures into inference systems and optimizing model efficiency, GPU utilization, and deployment reliability.
Model-written summary · the original posting is authoritative