Research Engineer, Infrastructure, Inference
Core
Design, optimize, and scale infrastructure systems to enable high-performance, cost-effective, and reliable inference for large AI models.
Role type
Senior IC infrastructure research engineer (AI inference systems)
Builds
Scalable inference stacks, orchestration frameworks, and compute fleets for AI model deployment
Domain
Artificial Intelligence / Distributed Systems / High-Performance Computing
Deliverable
production ML models
Required skills
Deep learning frameworks (PyTorch, JAX), inference serving systems (SGLang, vLLM), distributed orchestration (Kubernetes, Ray, SLURM), GPU optimization, system architecture design
Preferred skills
Large-scale model training support, distributed compute systems, GPU parallelism, hardware-aware optimizations, open-source contributions
Technologies
PyTorch, JAX, SGLang, vLLM, Kubernetes, Ray, SLURM, Triton, DeepSpeed, XLA
Responsibilities
Design and implement techniques to improve performance, latency, and throughput; Optimize codebase and compute fleet to utilize hardware FLOPs and memory; Extend orchestration frameworks for distributed inference; Establish standards for reliability and observability
Seniority
Senior, hands-on IC