Software Engineer, Platform & Inference

About the Company

Chai is a research lab working on generative models for molecular design. We are building AI infrastructure to engineer new medicines with speed and precision. Our mission is to unlock progress towards better cures and better science.

Responsibilities

• Own the serving stack to ensure latency, throughput, GPU efficiency, batching, and autoscaling across a multi-cloud GPU fleet
• Build infrastructure and software abstractions used to train, evaluate, and understand models
• Contribute to product-ready pipelines and experiment/observability tooling
• Maintain end-to-end ownership of 24/7 systems, including observability, alerting, and incident response

Requirements

• 4+ years building production systems with depth in performance, distributed systems, or ML serving
• Experience optimizing model inference (GPU utilization, batching, quantization, caching, or kernel-level work)
• Experience with 0-to-1 buildouts and 1-to-n scale-ups
• Ability to treat cost and efficiency as first-class constraints
• Strong systems judgment and ownership mindset