Software Engineer, Data and AI Platform

DoorDash•San Francisco, CA

4d•Remote

About The Position

DoorDash is building the world's most reliable on-demand, logistics engine for delivery! We're looking for talented engineers to help us develop a 24x7, global infrastructure system that powers DoorDash's three-sided marketplace of consumers, merchants, and dashers. The Data Platform’s Data User Experience Engineering team builds the products every DoorDash employee uses to answer questions with data. This portfolio includes our AI first reporting and authoring surface, Conversational analytics with AI, Semantic and Knowledge layer along with MCP and skills layer plus the full stack infrastructure that lets users and agents reach all of it. Our users span analysts, engineers, operators, and executives across DoorDash, Wolt, and Deliveroo, on a warehouse and OLAP footprint that includes Snowflake, Spark and Clickhouse. The team is a mix of engineers who have built AI & Data platforms and products at scale.

Requirements

B.S., M.S., or PhD. in Computer Science or equivalent
3+ years of industry experience in software engineering
Strong backend fundamentals, especially in Go, Python and the ability to own a service in production
Shipped an LLM-powered feature to real users, hands-on with retrieval and grounding and built or meaningfully extended an eval system
Built meaningful pieces of data platform products- semantic layers, data discovery, reporting applications, caching systems and data applications
Familiarity with a cloud-based environment such as AWS and with Kubernetes in production
Experience with MCP, agent frameworks, or tool-calling architectures in production
Experience with traditional and modern reporting or analytics tooling, data governance, controls and multi-tenant data platforms
Prompt and context optimization at scale - caching, token budgeting, cost/latency tuning

Nice To Haves

Full stack experience is a plus

Responsibilities

Own the full path from a question to an answer an operator can put in a deck without checking it twice.
Ship agentic analytics features to thousands of users where a wrong number is a real business decision made badly, and accuracy is the product.
Build a data platform for authoring, dashboard runtime, drill-down and cross-filter semantics, scheduling and alerting, content certification and permissions, and the embedding path that puts the same components in front of external users.
Stream large result sets to the browser, rendering dozens of interdependent tiles.
Build the AI experience inside that platform: agent-assisted query authoring, generated charts and widgets held to the same governance as hand-built ones.
Evolve the semantic layer: metric and dimension modeling, definition governance, lineage, and expose metadata in forms a model can actually reason over.
Own the query and adaptive caching path: planning and federation across different query engines and invalidation correctness, and safe execution under agent traffic that bursts and fans out.
Develop AI-enabled services and workflows, including self-serve tooling for creating, evaluating, and improving AI assistants.
Build and operate data discovery and metadata platforms that help users find the right datasets, dashboards, and metrics quickly and confidently.