Inference Infrastructure Engineer for Large-Scale AI

Causal; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Causal is building a Large Physics foundation Model and seeks infrastructure engineers for high-throughput, low-latency inference at scale in San Francisco. You will work on evaluating physical observations, backtesting, and large-batch workflows, collaborating with researchers to push model performance.

We value deep learning expertise, GPU-aware optimization, and production-grade engineering. Proficiency with PyTorch or JAX, Kubernetes-based orchestration, and open‑source inference tooling is

Qualifications

• Experience building or optimizing inference and serving systems for throughput and latency (e.g. TensorRT).
• Understanding of distributed compute, GPU parallelism, and hardware‑aware optimization.
• Deep familiarity with deep learning frameworks (e.g. PyTorch, JAX) and their underlying system architectures.
• Strong engineering skills: performant, maintainable code and the ability to debug complex codebases.

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.
• Extend orchestration frameworks (e.g. Kubernetes, Ray, Slurm) for distributed inference and large-batch evaluation sweeps.
• Establish standards for reliability, observability, and reproducibility across the inference stack, so every evaluation is trustworthy and repeatable.
• Collaborate with researchers to enable high-performance inference for novel architectures as they emerge.

Skills

Inference systems

Latency optimization

Distributed compute

GPU parallelism

PyTorch

JAX

Deep learning frameworks

Kubernetes

TensorRT

Tools

Ray

Slurm

Job description

Causal is building a Large Physics foundation Model and seeks infrastructure engineers for high-throughput, low-latency inference at scale in San Francisco. You will work on evaluating physical observations, backtesting, and large-batch workflows, collaborating with researchers to push model performance.

We value deep learning expertise, GPU-aware optimization, and production-grade engineering. Proficiency with PyTorch or JAX, Kubernetes-based orchestration, and open‑source inference tooling is