Senior ML Infra Engineer — GenAI Platform & Open-Weights

Visa Hunt; Sunnyvale, San Francisco (CA, CA); On-site; USD 137,100 - 299,300; Full time

Job summary

DoorDash’s GenAI Platform team builds the infrastructure that enables GenAI-powered products for DoorDash, Wolt, and Deliveroo. As a senior engineer, you will define the architecture for open-weight model serving, real-time endpoints, and high-throughput batch inference, while guiding fine-tuning pipelines and GPU utilization across production systems.

You will mentor engineers, collaborate with data scientists and platform teams, and push the cost/performance frontier in a fast-evolving AI

Qualifications

• B.S., M.S., or PhD. in Computer Science or equivalent.
• 6+ years of industry experience in software engineering.
• Deep backend engineering fundamentals, especially in Python and distributed systems.
• Experience operating systems in production, including observability, debugging, reliability, incident response, and performance/cost optimization.
• Hands-on experience with LLM inference and/or fine-tuning of open-weight models in production — serving and/or fine-tuning.

Responsibilities

• Lead the design of infrastructure that helps DoorDash teams move GenAI ideas from prototype to production, increasing velocity of business impact.
• Own and evolve our open-weights serving stack — real-time GPU endpoints, high-throughput batch inference, and fine-tuning alongside gateways, evals infra, guardrails, and cost attribution.
• Architect scalable, high-performance systems for model serving, batch inference, GPU autoscaling, and fine-tuning for real customer and internal automation use cases.
• Push the cost and latency frontier of GPU inference while giving product teams a clean choice across open-weight and closed-source models with reliability, observability, and cost controls.
• Build platforms that support rapid experimentation while meeting production standards for latency, scale, monitoring, SLOs, playbooks, and operational excellence.

Skills

Python

Distributed systems

LLM inference

GPU orchestration

Observability

Education

B.S., M.S., or PhD in Computer Science or equivalent

Tools

Kubernetes

AWS/GCP

Docker

TensorRT-LLM

Job description

DoorDash’s GenAI Platform team builds the infrastructure that enables GenAI-powered products for DoorDash, Wolt, and Deliveroo. As a senior engineer, you will define the architecture for open-weight model serving, real-time endpoints, and high-throughput batch inference, while guiding fine-tuning pipelines and GPU utilization across production systems.

You will mentor engineers, collaborate with data scientists and platform teams, and push the cost/performance frontier in a fast-evolving AI