Senior Engineer, Data & AI

Summary

Join Vox Media's data team as a Senior Engineer and contribute to the development and maintenance of our in-house content intelligence platform, Remix, and internal user memory system, VoxStar. This 12-month temporary, hybrid role blends back-end software development with data engineering and AI. You will build and maintain back-end services using Python, FastAPI, and Google Cloud technologies. You will also develop AI-powered applications using OpenAI and other APIs. Collaborate with stakeholders to translate problems into technical solutions and contribute to data engineering workflows. If you are a Python backend engineer with an interest in data and AI, or a data engineer who values high-quality code, we encourage you to apply.

Requirements

• An experienced Python backend engineer with an interest in data and AI or data engineer who cares about writing high quality production grade code
• Comfortable working in cloud-native environments to build and deploy APIs and services (preferably with FastAPI)
• Fluent in SQL and experienced with either analytics workflows in a cloud data warehouse or relational databases like Postgres
• Interested in applying generative AI and LLM tooling to real-world problems — you don’t need to be an expert, but you should be eager, curious, and self-directed
• Thoughtful about architecture, trade-offs, and how to make things easy for others to build on
• Comfortable working independently, collaborating across functions, and shifting between well-scoped projects and more open-ended discovery work

Responsibilities

• Build and maintain production-grade back-end services - our typical stack is Python, FastAPI, PostgreSQL (Google Cloud SQL), and Google Cloud Run
• Develop and evolve AI-powered applications , using a mix of APIs from OpenAI, Gemini, or similar providers and open-source tools and frameworks - we use Pydantic AI to build agentic systems
• Contribute to Remix, our content intelligence platform, enabling search, recommendations, personalized marketing , and other experiences both reader facing and internal
• Help maintain and extend VoxStar, our user data store and internal memory layer for personalized experiences
• Write well-structured code, tests, and documentation for services that operate at scale and support multiple use cases and play a key role in API design for these services
• Along with the rest of the team, create deployment workflows, tune database and query performance, and manage (lightweight) cloud infrastructure
• Collaborate with stakeholders in product, audience, and editorial to understand problems and translate them into technical solutions
• Occasionally contribute to data engineering workflows to build new datasets or tools , applying your Python and SQL skills outside of traditional back-end contexts - we use BigQuery, Dagster, dbt, Looker, and Hightouch

Preferred Qualifications

• Experience with semantic search , embedding-based retrieval , recommendation systems, and designing agentic systems
• Experience with data modeling and orchestration using tools like dbt and Dagster, or willing to learn
• Experience with multi-variate product testing at scale
• Experience modeling audience cohorts
• Exposure to LLM frameworks (Pydantic AI, Langchain)
• Proficient in REST API design, load testing, and deployment best practices
• Comfort with CI/CD, observability tooling, ML Ops

Benefits

• This is a temporary, full-time position
• This job is benefits-eligible
• We pride ourselves in providing comprehensive benefits to support all of our employees wherever they are in life
• This is a remote position