Causal
Member of Technical Staff — Inference Infrastructure
San Francisco · Staff+
Sponsorship not specifiedDetected 3 days ago
KubernetesDeep LearningPyTorchAI OrchestrationRoboticsProblem Solving
About the role
- Our founding team has built and deployed AI against the physical world in robotics, drug discovery, and particle physics at institutions like DeepMind, Waymo, Cruise, Insitro, Nabla Bio, and CERN.
- We look for infrastructure engineers who are excited to tackle unsolved problems.
- Progress on an LPM is gated by how fast we can evaluate it: large-scale backtesting against decades of physical observations, ensemble generation, and rollout evaluation across model scales.
Responsibilities
- Build high-throughput inference systems for large-scale evaluation, backtesting, and scoring against historical physical observations
- Design and implement techniques that improve latency, throughput, and efficiency for real-time inference
- Optimize the inference stack to fully utilize hardware FLOPs, bandwidth, and memory
- Collaborate with researchers to enable high-performance inference for novel architectures as they emerge
- Experience building or optimizing inference and serving systems for throughput and latency (e.g. TensorRT)
Requirements
- We value a relentless approach to problem-solving, rapid execution, and the ability to quickly learn in unfamiliar domains.
- Strong engineering skills: performant, maintainable code and the ability to debug complex codebases
- We believe that scaling on physics will enable an understanding of causality required to predict and control physical systems, starting with weather.
Nice to have
- contributions to open-source inference or systems infrastructure (e.g. vLLM, SGLang, Triton)
Skills
- performant, maintainable code and the ability to debug complex codebases
- Bonus: contributions to open-source inference or systems infrastructure (e.g. vLLM, SGLang, Triton)
Benefits
- Deep familiarity with deep learning frameworks (e.g. PyTorch, JAX) and their underlying system architectures
Company info
- Your mission is to make inference so fast and cheap that evaluation never gates research.
- What we're looking for
This listing is sourced directly from Causal's careers page and normalized into a canonical job model.