Senior/Staff Deep Reinforcement Learning Engineer

Our DD Labs team builds real-time autonomous delivery systems. The Planning & Decision-Making group is investing heavily in deep reinforcement learning to move beyond classical planning, learning policies that generalize across novel driving scenarios, handle long-tail edge cases, and improve continuously from large-scale fleet data. Our models jointly handle prediction and planning in a single unified architecture. Our stack is pure JAX end-to-end: the same code you train with is the code that runs on the robot. No C++ rewrites, no TensorRT export. A new policy goes from training to on-vehicle deployment in minutes.

The Storage teams build and operate online stateful systems and abstractions that are reliable, efficient, secure and easy to use for DoorDash Engineering. The teams are responsible for understanding Product Engineering’s evolving needs and developing platform and infrastructure capabilities to serve them. The team currently supports CockroachDB, Cassandra, Kafka and Redis as well as data abstraction services to reduce the complexity of interacting with storage systems for Product Engineers.

As a Senior/Staff Deep RL Engineer, you will design, train, and deploy deep reinforcement learning policies that make real-time driving decisions for our autonomous vehicles. You will own the full lifecycle, from problem formulation and reward design through large-scale distributed training to on-vehicle inference. You'll help define how learned components compose with the rest of the autonomy stack to produce robust, shippable behavior.

• Formulate complex driving tasks as RL problems with well-shaped reward functions and expressive state/action representations.
• Design and train model-based deep RL agents using GPU-accelerated simulation at massive scale, including improving the simulator itself.
• Build and maintain distributed training infrastructure in JAX across large compute clusters.
• Build agentic optimization systems that automatically improve code, run experiments, analyze metrics, and iterate on RL policies with minimal human intervention.

We’re hiring a Data Solutions Engineer with deep expertise in distributed databases, particularly Apache Cassandra, Redis, Kafka, and database agnostic abstractions. In this role, you will design, optimize, and scale distributed data access layers that power DoorDash’s most critical systems, ensuring high availability, low latency, and fault tolerance.

You’ll serve as a hands-on architect and technical partner to product engineering and infrastructure teams, helping translate complex business requirements into resilient and scalable data models. Your work will directly influence the evolution of Taulu, DoorDash’s unified storage abstraction layer, by shaping best practices and identifying platform gaps through real world engagements.

This is a high-impact, cross functional role that combines deep technical expertise with a customer centric approach. You’ll lead solutioning engagements from design through production, drive the adoption of Taulu modeling best practices, and ensure that our systems meet goals around reliability, cost efficiency, and velocity. You must be located in San Francisco, Sunnyvale, Seattle or New York for this hybrid opportunity. 

• Design and implement highly scalable, fault tolerant distributed database solutions using Taulu, Apache Cassandra, Redis, Kafka, and other paved path storage solutions. 
• Architect and optimize multi-region, globally distributed systems to meet our high standards for availability, latency, and throughput.
• Lead data modeling, performance tuning, and capacity planning for large-scale, mission-critical storage workloads.
• Partner with product engineering and infrastructure teams to deeply understand domain specific data needs and guide them in adopting paved path storage solutions.
• Serve as the DRI for solutioning engagements, owning modeling in Taulu from experimentation through launch and scale.
• Shape the evolution of Taulu by identifying abstraction gaps and converting customer feedback into platform improvements.
• Apply workload-aware design patterns, including caching strategies, partitioning, and consistency tuning to improve performance and efficiency.
• Drive adoption of operational best practices across observability, schema design, capacity planning, and cost optimization across storage systems.
• Promote clarity and continuity by contributing to solutioning playbooks, decision logs, and architectural documentation.

• BS/MS/PhD in CS, EE, Robotics, or a related field, with a strong foundation in reinforcement learning and deep learning.
• You have proficiency in using AI coding tools (e.g., Claude Code, Codex, Cursor) in the full software development lifecycle, including designing, generating code, testing, monitoring and releasing software
• Hands-on experience training RL agents at scale, ideally in robotics, autonomous driving, or other real-time decision-making domains.
• Proficiency in JAX or a similar functional ML framework; comfort with JIT compilation, vectorized environments, and GPU-accelerated simulation.
• Deep grasp of core RL concepts: policy gradients, value functions, exploration-exploitation, model-based RL, reward shaping, and sim-to-real transfer.
• Data-driven mindset: comfortable building experiment pipelines, analyzing training runs, and letting metrics guide architectural decisions.

• You have 10+ years of experience designing and scaling distributed data systems, with deep expertise in NoSQL technologies like Apache Cassandra, DynamoDB, or ScyllaDB.
• You have a strong command of distributed system concepts such as replication, partitioning, tunable consistency, and failure recovery.
• You’ve led data modeling efforts for high-throughput, low-latency workloads and understand the real-world trade-offs involved in NoSQL schema design.
• You are experienced with caching technologies like Redis or Memcached and know how to layer them effectively over storage systems to optimize for performance and cost.
• You have a customer-first mindset, and thrive when working closely with product and platform teams to translate complex requirements into clean, scalable data models.
• You are skilled at communicating complex architecture decisions and building alignment across infrastructure and product engineering organizations.
• You have a track record of mentoring engineers, influencing data architecture at scale, and fostering best practices in reliability, observability, and data access patterns.
• You document decisions, share learnings, and take pride in contributing to reusable playbooks and durable frameworks for others to build upon.
• Bonus: You’ve worked on or contributed to open-source distributed databases.  

• Publications at top venues (NeurIPS, ICML, ICLR, CoRL, RSS, ICRA) on RL or learned planning.
• Experience building or working with GPU-accelerated simulators for RL training.
• Track record of shipping a learned component in a production robotics or autonomous vehicle stack.

Notice to Applicants for Jobs Located in NYC or Remote Jobs Associated With Office in NYC Only

We used Covey as part of our hiring and/or promotional process for jobs in NYC and certain features may qualify it as an AEDT in NYC. As part of the hiring and/or promotion process, we provided Covey with job requirements and candidate submitted applications. We began using Covey Scout for Inbound from August 21, 2023, through December 21, 2023.  We resumed using Covey Scout for Inbound again on June 29, 2024, and ceased using Covey Scout for Inbound on April 30, 2026.

The Covey tool has been reviewed by an independent auditor. Results of the audit may be viewed here: https://getcovey.com/nyc-local-law-144.