Lead GenAI Infrastructure Engineer (Open‑Weights, GPU)

DoorDash; San Francisco (CA); On-site; USD 170,000 - 250,000; Full time

Benefits offered by this job

401(k) with employer matching

Paid parental leave

Health, dental and vision insurance

Wellness benefits

Job summary

DoorDash’s GenAI Platform team sits within Machine Learning Platform and builds the shared infrastructure that helps teams safely bring GenAI-powered products to production. Our mission is to increase the velocity of business impact from GenAI.

A central pillar of that work is running frontier open‑weight LLMs and VLMs ourselves — delivering large cost and latency wins with real-time GPU serving and fine-tuning.

Qualifications

• 6+ years of software engineering experience.
• Strong backend fundamentals in Python and distributed systems.
• Hands-on production services and ML infrastructure experience.

Responsibilities

• Lead design and architecture of open-weights model platform.
• Set technical direction across serving engines, fine-tuning and training pipelines.
• Mentor engineers and collaborate with ML, product, data scientists, and platform teams.
• Ensure latency, scale, and operational excellence for production deployments.

Skills

Python

Distributed systems

Production services design

Observability & reliability

LLM inference/fine-tuning

Technical leadership

AI coding tools (Claude Code, Codex, C

Education

BS/MS/PhD in Computer Science or equivalent

Tools

Kubernetes

AWS/GCP

GPUs

Modal

Job description

DoorDash’s GenAI Platform team sits within Machine Learning Platform and builds the shared infrastructure that helps teams safely bring GenAI-powered products to production. Our mission is to increase the velocity of business impact from GenAI.

A central pillar of that work is running frontier open‑weight LLMs and VLMs ourselves — delivering large cost and latency wins with real-time GPU serving and fine-tuning.