Member of Technical Staff — Inference Infrastructure

The role

You will build high-throughput inference systems for large-scale evaluation and backtesting. You will optimize the inference stack and extend orchestration frameworks to support distributed inference.

What you will do

• Build high-throughput inference systems for large-scale evaluation, backtesting, and scoring
• 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 for distributed inference and large-batch evaluation sweeps
• Establish standards for reliability, observability, and reproducibility across the inference stack
• Collaborate with researchers to enable high-performance inference for novel architectures

Required qualifications

• 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 underlying system architectures
• Strong engineering skills: performant, maintainable code and the ability to debug complex codebases

Nice to have

• contributions to open-source inference or systems infrastructure (e.g. vLLM, SGLang, Triton)

About the company

Causal is building a Large Physics foundation Model to achieve general causal intelligence. The founding team has built and deployed AI at institutions like DeepMind, Waymo, Cruise, Insitro, Nabla Bio, and CERN.