ML Serving Platform Engineer: Scale & Self-Serve Infra

DoorDash, Inc.; San Francisco, Sunnyvale, Seattle (CA, CA, WA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

401(k) with employer matching

Paid parental leave

Wellness benefits

Medical, dental, and vision benefits

Job summary

DoorDash, Inc. in San Francisco is seeking an experienced software engineer to help build the next generation of our ML serving platform.

You will work on connecting request routing, feature retrieval, and model inference on CPU/GPU infrastructure, addressing latency and scale challenges. You will own projects from design to production, collaborating with modelers and platform teams, and contributing to self-serve tooling and open source integrations.

Qualifications

• 2+ years of software engineering experience building production services.
• Proficiency in one of Java, Kotlin, Go, C++, or Python.
• Understanding distributed systems, concurrency, networking, timeouts, and performance trade-offs.
• Degree in CS or related field, or equivalent practical experience.

Responsibilities

• Build and maintain production services for the ML serving platform.
• Improve latency, reliability, and resource efficiency.
• Collaborate with internal teams to understand modeling requirements.
• Own design, testing, rollout and on-call production support.

Skills

Java

Kotlin

Go

C++

Python

Education

Bachelor's degree in Computer Science or related field

Job description

DoorDash, Inc. in San Francisco is seeking an experienced software engineer to help build the next generation of our ML serving platform.

You will work on connecting request routing, feature retrieval, and model inference on CPU/GPU infrastructure, addressing latency and scale challenges. You will own projects from design to production, collaborating with modelers and platform teams, and contributing to self-serve tooling and open source integrations.