You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
DoorDash USA

Senior Software Engineer, ML Serving Platform

  • Office
  • 6+ years

Salary

$167,800 - 246,800/ year

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

Predictions run at tens of millions per second across the company's brands, feeding search, recommendations, advertising, and logistics.

The ML Serving Platform team builds request routing, online feature lookup, and CPU and GPU inference, so ML and product groups can deploy and run their own models.

The company is a technology and logistics business that began with door-to-door delivery.

This is a hands-on senior role leading core serving work, with a particular interest in engineers who have scaled ranking and recommendation systems in production.

In the first 6 to 12 months, you will help enable new ranking and recommendation models, including generative ones, in live traffic. Success means faster adoption while meeting quality, latency, reliability, and cost targets.

You will make architecture decisions, write production code, and coordinate delivery with ML, product, and compute partners.

Responsibilities

  • Own projects from a customer problem through design, build, and rollout, coordinating engineers, mentoring peers, and shaping the roadmap.
  • Find inference bottlenecks using production traces, load tests, and CPU and GPU profiling, and work with model owners on trade-offs between quality, tail latency, throughput, and cost.
  • Work with Compute on capacity, placement, and scaling, factoring in request complexity, cache state, GPU memory, and model startup time.
  • Build self-serve APIs and deployment workflows for models, runtime dependencies, features, and versioned state, including validation, safe rollout, and rollback.
  • Evaluate open source and vendor tools, decide whether to build or adopt, and work with their maintainers and vendors.
  • Keep services reliable through service objectives, observability, on-call, incident response, and follow-up, and reduce repetitive operational work through automation.

Requirements

  • 6+ years of experience designing, building, and operating production infrastructure or distributed systems.
  • Hands-on experience serving large or complex neural models online, accountable for latency, availability, and resource efficiency.
  • Strong distributed systems fundamentals and proficiency in a backend or systems language such as Python, Go, Java, Kotlin, or C++.
  • Understanding of inference trade-offs across batching, concurrency, caching, memory, and CPU/GPU utilization, and the ability to diagnose production bottlenecks.
  • Experience running services on Kubernetes or comparable infrastructure, including resource configuration, autoscaling, and failure recovery.
  • A record of leading substantial projects through ambiguity, working with fast-moving ML or product teams, and helping other engineers grow.
  • A degree in Computer Science or a related field, or equivalent practical experience.
  • Experience integrating or extending inference tools such as Triton Inference Server or PyTorch.
  • Experience with multi-GPU inference, model parallelism, model-aware caching, or accelerator scheduling.
  • Experience building model workflows, deployment tooling, or instrumentation with Metaflow, Helm, or OpenTelemetry.
  • Production serving depth and engineering judgment matter most; experience with every listed technology is not required.

Conditions

Starting pay falls within the range below and depends on factors such as skills, experience, qualifications, work location, and market conditions. Base salary is localized by work location, and ranges may change.

The national base pay range for this role in the United States, including Illinois and Colorado, is $167,800 to $246,800 USD.

Compensation also includes possible equity grants; ask your recruiter for details.

Salaried roles receive flexible paid time off or vacation plus 80 hours of paid sick time per year. Hourly roles accrue vacation at 1 hour for every 25.97 hours worked (about 6.7 hours a month at 40 hours a week, or about 3.4 hours a month at 20 hours a week) and paid sick time at 1 hour for every 30 hours worked (about 5.8 hours a month at 40 hours a week, or about 2.9 hours a month at 20 hours a week).

The company is an equal-opportunity employer that considers all qualified applicants, including those with arrest or conviction records, and accommodation requests can be made to your recruiting contact at first contact.

Benefits

  • 401(k) plan with employer matching.
  • 16 weeks of paid parental leave.
  • Wellness benefits and wellness expense reimbursement.
  • Commuter benefits match.
  • Paid time off and paid sick leave in line with applicable laws, such as the Colorado Healthy Families and Workplaces Act.
  • Medical, dental, and vision coverage, including premium healthcare.
  • 11 paid holidays.
  • Disability and basic life insurance.
  • Family-forming assistance.
  • A mental health program, among other benefits.

Where you’d work

From the office

About the company

DoorDash USA

  • Industry: Logistics

Offices in San Francisco, United States, Sunnyvale, United States, Seattle, United States

Also hiring in New York, United States, Oakland, United States, New York City, United States and 12 more places

7 of their 56 open roles are remote

Your chances

We've checked whether it's still hiring and how crowded it is.

  • 21 checks run
  • 0 red flags

Still hiring?

14 checks

No red flags

How crowded?

7 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details13 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • Python
  • Kubernetes
  • PyTorch
Seniority
Senior
Type
Full-time
Equity
Equity offered
Industry
Logistics
Specialty
ML
Show 7 more factsShow less

Role

Category
Data & Analytics
Specialty
ML
Seniority
Senior
Experience
6+ years
Tech stack
  • Python
  • Kubernetes
  • PyTorch

Location

Work model
Office
Region
United States
Offices
  • San Francisco, United States
  • Sunnyvale, United States
  • Seattle, United States

Compensation

Salary
$167,800 - 246,800 / year
Pay period
Annual
Equity
Equity offered

Employment

Type
Full-time

Company

Industry
Logistics

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason