ML Engineer, Logistics & Delivery AI

DoorDash USA; San Francisco (CA); Hybrid; USD 167,000 - 299,000; Full time

Benefits offered by this job

401(k) plan with employer matching

16 weeks of paid parental leave

Wellness benefits

Commuter benefits match

Paid time off & paid sick leave

Job summary

DoorDash Drive ML Engineers design and ship production ML systems, from features to deployment, monitoring, and iteration. You’ll work on ETA prediction, optimization, and logistics decisions using large-scale signals and multimodal AI techniques across diverse problem areas.

You’ll collaborate with software engineers, product managers, and data scientists, applying DL, RL, and LLM/VLM approaches to improve reliability and marketplace efficiency in a fast-paced environment.

Qualifications

• 5+ years of industry experience building and shipping production ML systems.
• Strong experience with PyTorch and distributed data processing.
• End-to-end ML systems: development, deployment, monitoring, and maintenance.
• Proficiency in Python and ML infrastructure tooling.
• Expertise in at least one: DL, RL, optimization, LLMs or VLMs.

Responsibilities

• Own ML systems end-to-end from feature engineering to deployment and monitoring.
• Build models for ETA prediction, optimization, and decision-making in logistics.
• Experiment, iterate, and run online tests to improve performance.
• Collaborate with engineers, PMs, data scientists, and platform teams.

Skills

PyTorch

Spark

Airflow

Python

Deep Learning

Reinforcement Learning

Optimization

LLMs / VLMs

Education

Bachelor's degree

Master's degree

PhD

Tools

Spark

Airflow

TensorFlow

Job description

DoorDash Drive ML Engineers design and ship production ML systems, from features to deployment, monitoring, and iteration. You’ll work on ETA prediction, optimization, and logistics decisions using large-scale signals and multimodal AI techniques across diverse problem areas.

You’ll collaborate with software engineers, product managers, and data scientists, applying DL, RL, and LLM/VLM approaches to improve reliability and marketplace efficiency in a fast-paced environment.