Starburst
Applied AI Research Engineer
About this role
Starburst is hiring an Applied AI Research Engineer to build the intelligence layer for AIDA, their AI agent platform. You'll design grounding systems, optimize retrieval pipelines, create evaluation frameworks, and ship production systems that make AI agents more correct and trustworthy.
What you'll do
- Design and build grounding systems connecting agent reasoning to verified enterprise data sources
- Build and optimize retrieval pipelines (RAG, hybrid search, structured query generation) for accuracy and latency
- Define data representation strategies for heterogeneous enterprise data including catalogs, schemas, and lineage
- Create evaluation frameworks with automated benchmarks, regression suites, and human evaluation protocols
- Establish quality metrics and dashboards tracking agent correctness over time
- Build feedback loops where user interaction data informs evaluation datasets and grounding improvements
What they're looking for
- Information retrieval and NLP
- Production RAG and grounding systems
- Evaluation methodology and benchmark design
- Python programming
- Vector databases and embedding models
- LLM APIs and prompt engineering
- Text-to-SQL and structured query generation
- Statistical analysis and experimental design
Benefits
- Equity packages (ISOs)
- Comprehensive benefits offering
- Opportunity to work at research/systems boundary
- Weekly shipping cadence and startup speed
- End-to-end ownership of experiments from hypothesis to production
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.
Starburst
Starburst provides technical support and deployment services for enterprise customers, including custom solutions and system upgrades. The company is hiring Technical Support Engineers to troubleshoot issues, serve as subject matter experts for major accounts, and collaborate across teams to enhance customer experience.
- Website
- starburst.io
Likely interview questions
- Describe a production RAG or grounding system you built. What were the key technical challenges and how did you measure success?
- How would you design an evaluation framework to track agent correctness for a question-answering system over enterprise data?