Relativity Space
AI Software Engineer II
About this role
Relativity Space seeks an AI Software Engineer II to build AI-powered applications and agents for their rocket factory and launch operations. You'll work across the full development lifecycle using foundation models, modern Python/TypeScript stacks, and cloud infrastructure to create reliable, production-grade systems that empower engineers and operators.
What you'll do
- Design and implement AI applications and agents using foundation models like Claude
- Build full-stack solutions from concept through production deployment using Python, React, and TypeScript
- Develop and iterate on LLM evaluation tooling and reliability practices for AI systems
- Collaborate with cross-functional teams including design, manufacturing, and launch operations to define and ship solutions
- Own the development of data pipelines and vector search infrastructure for AI applications
- Follow agile practices with continuous integration and deployment of quality software
What they're looking for
- Python and backend development
- React and TypeScript for frontend work
- Foundation models and LLM frameworks (Claude, agent orchestration)
- Cloud infrastructure (AWS, Kubernetes, Terraform)
- Data engineering (Spark, DuckDB, Redshift, DBT, vector databases)
- SQL and database design (Postgres, MongoDB)
- Agile software development and CI/CD practices
- Cross-functional collaboration and stakeholder communication
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Relativity Space
Relativity Space develops the Terran R reusable rocket and is hiring engineers to design, manufacture, and launch it. The company seeks Manufacturing Engineers, Launch Integration Engineers, Vehicle Structures Engineers, and Avionics Hardware Engineers to work on critical flight systems, production processes, and launch operations at Cape Canaveral.
- Website
- relativityspace.com
Likely interview questions
- Can you describe your experience building and deploying production AI applications? What challenges did you face?
- How have you approached evaluating and monitoring LLM-based systems in production?