Software Engineer, Platform & Inference

📋 Job Overview

Application for Software Engineer, Platform & Inference at Chai Discovery. Chai builds the design suite for molecules, training frontier models that learn the underlying foundations of biochemical structure and interaction to help scientists move faster and pursue targets that other methods cannot reach.

🏢 About Chai Discovery

Chai builds the design suite for molecules. We train frontier models that learn the underlying foundations of biochemical structure and interaction, so scientists can move faster and pursue targets that other methods cannot reach. AI is reinventing life sciences the same way it reinvented software engineering, and Chai is at the forefront of this shift. Leading pharmaceutical companies like Eli Lilly, Pfizer, and Novartis are rapidly adopting our platform to power their drug discovery programs. Our mission is to accelerate progress towards new cures and better science, and there are countless interesting problems on the road ahead.

🎯 The Role

Platform engineers make Chai's models fast, cheap, and reliable at scale, and enable the outer loop that accelerates research: the infrastructure and software abstractions used to train, eval, and understand models. You'll own the serving stack that turns our frontier models into a product scientists depend on: latency, throughput, GPU efficiency, batching, and autoscaling across a large multi-cloud GPU fleet. You'll also contribute to the work that enables turning raw models into product-ready pipelines, and the experiment and observability tooling that lets a researcher ship faster. You've built high-performance services that developers love, moved ML systems into production at scale, and can see around corners before they become outages. You'll work closely with the researchers who train the models, the product engineers who build on them, and the commercial team deploying them to the world's largest pharma companies.

✅ Key Responsibilities

• Own the serving stack that turns our frontier models into a product scientists depend on: latency, throughput, GPU efficiency, batching, and autoscaling across a large multi-cloud GPU fleet.
• Contribute to the work that enables turning raw models into product-ready pipelines.
• Develop experiment and observability tooling that lets a researcher ship faster.
• Build high-performance services that developers love.
• Move ML systems into production at scale.
• Work closely with researchers, product engineers, and the commercial team.

📌 Required Qualifications

• 4+ years building production systems, with real depth in performance, distributed systems, or ML serving.
• Experience optimizing model inference: GPU utilization, batching, quantization, caching, or kernel-level work.
• A platform mindset: you like building the tools and abstractions that make other engineers and researchers faster.
• End-to-end ownership of 24/7 systems, including observability, alerting, and incident response.
• Experience across both 0-to-1 buildouts and 1-to-n scale-ups, with an always-evolving playbook you bring wherever you go.
• The instinct to treat cost and efficiency as first-class constraints, not afterthoughts.

⭐ Desirable Experience

• A background in biology is not required. What makes the difference is technical excellence, curiosity about the domain, and grit.

🎁 Benefits

The opportunity to work at the vanguard of AI research and frontier biology, with world-class people, on a mission that matters. We protect & promote a culture of high velocity and ownership. We compensate our team accordingly.