Software Engineer, Platform & Inference

Menlo Ventures; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Competitive compensation

Ownership culture

World-class team

Job summary

Chai Discovery is building a design suite for molecules and AI-driven biology. Platform engineers own the serving stack that makes frontier models fast, reliable, and scalable across a multi-cloud GPU fleet.

You'll optimize latency, throughput, and GPU efficiency, and turn models into product-ready pipelines used by researchers. You'll work with researchers, product engineers, and the commercial team to ship systems that researchers depend on and to drive observability, incident

Qualifications

• 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.
• 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.

Responsibilities

• Own the serving stack that turns frontier models into a product researchers depend on: latency, throughput, GPU efficiency, batching, and autoscaling across a large multi-cloud GPU fleet.
• Contribute to pipelines and observability tooling that lets researchers ship faster.
• Work closely with researchers, product engineers, and the commercial team deploying them to the world's largest pharma companies.
• Drive reliability and performance in production systems with 24/7 uptime.
• Collaborate to continuously evolve the platform with a focus on cost efficiency.

Skills

Production systems

GPU optimization

Platform mindset

Observability & incident response

End-to-end ownership

Cost optimization

Job description

About Chai Discovery

Chai is a research lab working on AI to unlock biology. Our models design new molecules for new medicines. We are changing how biologists develop drugs, just as language models are changing how engineers write code. Our vision is a design suite for molecules, with applications across life sciences, agriculture, materials and beyond.

Our founders have been at the forefront of this field from the beginning. We are backed by Thrive, General Catalyst, OpenAI, Dimension and other tier-one investors. We partner with global life sciences companies like Eli Lilly on deals that are transforming industry.

We are known for talent density, rigorous research and pace of execution.

About 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.

About you

We index on systems judgment, ownership, and the scars that come from having run production infrastructure before. We're looking for engineers who get obsessed with hard problems and don't give up easily. We look for:

• 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

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

We offer

The opportunity to work at the leading edge of AI research, with world‑class people, on a mission that matters. We protect & promote a culture of high velocity and ownership. We offer highly competitive compensation.