Causal Labs
Member of Technical Staff — Inference Infrastructure
San Francisco +1 · On-site · Staff · Full-time · Posted Jul 19, 2026
- Location
- San Francisco
Singapore
About the job
Build and optimize inference infrastructure so researchers can rapidly evaluate large physics foundation models against historical physical observations.
What you'll do
- Build high-throughput inference systems for evaluation, backtesting, and scoring.
- Optimize inference latency, throughput, and hardware utilization; extend distributed orchestration for large evaluation sweeps.
- Establish reliability, observability, and reproducibility standards, and collaborate with researchers on inference for new architectures.
What they ask for
- Experience building or optimizing inference and serving systems for throughput and latency.
- Understanding of distributed compute, GPU parallelism, and hardware-aware optimization.
- Deep familiarity with deep learning frameworks and their system architectures.
- Strong engineering skills, including writing maintainable, performant code and debugging complex codebases.
Nice to have
- Contributions to open-source inference or systems infrastructure, such as vLLM, SGLang, or Triton.
Tools
TensorRT, Kubernetes, Ray, Slurm, PyTorch, JAX, vLLM, SGLang
AI focus
Develop inference infrastructure for a Large Physics foundation Model to evaluate, backtest, and score predictions about physical systems.
Model-written summary · the original posting is authoritative