About this role
Designing and building grounding systems that connect agent reasoning to verified enterprise data sources forms the foundation of daily work for this position. Operating at the research and systems boundary, the successful candidate experiments with academic rigor while deploying results using production engineering standards. Responsibilities include defining data representation strategies across heterogeneous enterprise catalogs, optimizing retrieval pipelines, and building evaluation infrastructure.
Starburst builds the AI layer for products like AIDA, focusing on natural language interfaces that query distributed data environments without consolidation costs. Functioning with startup speed inside an established enterprise, the team ships updates weekly and measures outcomes systematically. This represents the inaugural dedicated research engineering hire for the group, making it suitable for an autonomous practitioner who bridges scientific inquiry with robust code execution.
What you will do
- Design and build grounding systems that connect agent reasoning to verified enterprise data sources.
- Build and optimize retrieval pipelines for accuracy and latency across RAG, hybrid search, and structured query generation.
- Define data representation strategies that preserve semantic fidelity across heterogeneous enterprise catalogs, schemas, and lineage.
- Create evaluation frameworks including automated benchmarks, regression suites, and human evaluation protocols.
- Convert validated research findings into production systems that ship directly to users.
- Establish quality metrics and dashboards that track agent correctness week over week.
- Build feedback loops where user interaction data flows back into evaluation datasets and informs grounding improvements.
What you need
- Bring three or more years of experience in information retrieval, NLP, knowledge representation, or applied machine learning research.
- Possess production experience building RAG, grounding, or retrieval systems rather than basic prototypes or demos.
- Demonstrate strong evaluation methodology covering benchmark design, statistical analysis, and reproducible experiments.
- Maintain comfort operating at the research and systems boundary by reading academic papers and shipping code.
- Show Python fluency along with practical experience using vector databases, embedding models, and large language model APIs.
- Present a track record of converting research insights into shipped production systems.
- Accommodate up to 25 percent in-person travel for onboarding, team offsites, customer engagements, and company events.
Nice to have
- Experience with enterprise data systems including SQL engines, data catalogs, and schema metadata
- Familiarity with text-to-SQL or structured query generation
- Published research or open-source contributions in IR, NLP, or evaluation methodology
- Experience designing evaluation pipelines that run in CI/CD
- Familiarity with JVM-based systems
Benefits
- Competitive salary range of $215,000 to $270,000 USD
- Equity packages including ISOs
- Comprehensive benefits offering
- Competitive pay
- Attractive stock grants
- Flexible paid time off
Skills and tech stack
Questions candidates ask
What is the salary range for this role?
The salary range for this role is $215,000 to $270,000 USD. Actual compensation packages are determined based on relevant skills, experience, education, training, and specific work location.
What travel is required for the position?
This role requires 25% in-person travel for purposes including new hire onboarding, team and department offsites, customer engagements, and other company events. Actual travel expectations may vary by role and business needs.
What does the team actually build?
The team builds the AI layer for Starburst's products, including AIDA. They design agents that let users ask questions in natural language and get accurate, grounded answers backed by their actual data.
What kind of equity and benefits are provided?
All employees receive equity packages in the form of ISOs and have access to a comprehensive benefits offering. This includes a variety of benefits like competitive pay, attractive stock grants, and flexible paid time off.