Senior ML Infra Engineer: Open-Weights & GPU Inference

DoorDash USA; San Francisco (CA); On-site; USD 137,100 - 201,600; Full time

Benefits offered by this job

401(k) plan with employer matching

16 weeks of paid parental leave

Wellness benefits

Job summary

DoorDash USA in San Francisco is searching for a senior engineer to lead the design and architecture of its Generative AI infrastructure. You will oversee the model serving stack, ensuring performance and reliability while mentoring your team.

You should have a strong background in backend engineering, particularly in Python and distributed systems, along with technical leadership experience. This role also offers a generous benefits package, including flexible paid time off and a 401(k) plan.

Qualifications

• 6+ years of industry experience in software engineering.
• Experience operating systems in production, including observability and performance optimization.
• Deep hands-on experience with LLM inference and fine-tuning.

Responsibilities

• Lead the design of infrastructure for Generative AI at DoorDash.
• Own and evolve the open-weights serving stack and related platforms.
• Architect scalable, high-performance systems for model serving.

Skills

Backend engineering fundamentals

Python

Distributed systems

Technical leadership

AI coding tools

Education

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

Tools

Kubernetes

AWS/GCP

Job description

DoorDash USA in San Francisco is searching for a senior engineer to lead the design and architecture of its Generative AI infrastructure. You will oversee the model serving stack, ensuring performance and reliability while mentoring your team.

You should have a strong background in backend engineering, particularly in Python and distributed systems, along with technical leadership experience. This role also offers a generous benefits package, including flexible paid time off and a 401(k) plan.