Applied AI Research Engineer
What you need
Tech
Experience
- 3+ yrs IR/NLP/ML research
- Production RAG/retrieval systems
What you'll do
- Design grounding systems
- Build retrieval pipelines
- Create evaluation frameworks
- Ship research to production
About Starburst
Starburst delivers enterprise intelligence at scale by giving organizations secure, governed access to all their data, wherever it lives. Built for distributed data environments, Starburst helps enterprises power AI and analytics without the cost and complexity of traditional data consolidation. With open standards including Trino and Apache Iceberg, Starburst enables trusted access to complete enterprise context while helping organizations avoid vendor lock-in. Leading global enterprises trust Starburst to fuel AI, analytics, and enterprise intelligence. Learn more at starburst.ai.
About the Team
We build the AI layer for Starburst's products, including AIDA. We design agents that let users ask questions in natural language and get accurate, grounded answers backed by their actual data. We operate with startup speed inside an enterprise company, shipping weekly and measuring results. This is the first dedicated research engineering hire on the team.
Role Summary
You will own the intelligence layer that makes AIDA's agents correct, trustworthy, and measurably better over time. The work spans information retrieval, knowledge representation, and evaluation science. You will turn ambiguous notions of "agent quality" into clear metrics, build the grounding systems that connect agent reasoning to verified data, and create the evaluation infrastructure that makes quality a first-class engineering discipline.
You will operate at the research/systems boundary: running experiments with academic rigor and shipping results with production engineering discipline. Research and engineering are not separate tracks here. You will own experiments end to end, from hypothesis through production deployment.
As an Applied AI Research Engineer at Starburst, you will:
- Design and build grounding systems that connect 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 that preserve semantic fidelity across heterogeneous enterprise data (catalogs, schemas, lineage)
- Create evaluation frameworks: automated benchmarks, regression suites, human evaluation protocols
- Convert validated research findings into production systems that ship 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
Some of the things we look for:
- 3+ years of experience in information retrieval, NLP, knowledge representation, or applied ML research
- Production experience building RAG, grounding, or retrieval systems (not prototypes or demos)
- Strong evaluation methodology: benchmark design, statistical analysis, reproducible experiments
- Comfort operating at the research/systems boundary: you read papers and you ship code
- Python fluency; experience with vector databases, embedding models, LLM APIs
- Track record of converting research insights into shipped production systems
Preferred Qualifications
- Experience with enterprise data systems (SQL engines, data catalogs, 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
- Ability to Travel: This role will require 25% in-person travel for purposes including but not limited to new hire onboarding, team and department offsites, customer engagements, and other company events. Actual travel expectations may vary by role and business needs.
Starburst is dedicated to maintaining fair and equitable compensation practices. The salary range provided for this role reflects the minimum and maximum targets for candidates across all U.S. locations and could be inclusive of variable compensation, such as commission or bonus. All employees receive equity packages (ISOs) and have access to a comprehensive benefits offering. Actual compensation packages are determined based on relevant skills, experience, education and training, and specific work location. For more information, connect with the recruiting team or Hiring Manager during the process as they can provide more detailed information about the salary range.
Build your career at Starburst
All-Stars have the opportunity and freedom to realize their true potential. By building alongside top talent, we’re empowered to take ownership of our careers and drive meaningful change. Anchored in industry-proven technology and unprecedented success, All-Stars are taking on the challenge everyday to disrupt our industry – and the future.
Our global workforce is supported by a competitive Total Rewards program that reflects our commitment to a rewarding and supportive work environment. This includes a variety of benefits like competitive pay, attractive stock grants, flexible paid time off, and more.
We are committed to fostering an intentional, inclusive, and diverse culture that drives deep engagement, authentic belonging, and an exceptional All-Star experience. We believe that diversity of thought, perspective, background and experience will enable us to own what we do, drive our success and empower our All-Stars to show up authentically.
Starburst provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state
or local laws.
Optimize your resume for this job
Get a match score and the keywords you're missing
About Starburst
Starburst was founded by the inventors of OS Trino so that data-driven companies could have a full-featured open data lakehouse platform powered by the #1 SQL analytics engine. Our end-to-end analytics platform includes the capabilities needed to discover, organize, consume, and share data with industry-leading price-performance for cloud and on-premises workloads. We believe the lakehouse should be the center of gravity, but support accessing data outside the lake when needed. With Starburst, teams can access more complete data, run scalable analytics, lower the cost of infrastructure, use tools best suited to their needs, and avoid vendor lock-in. Trusted by companies like Apache Corporation, Comcast, Doordash, DBS Bank, and VMware, Starburst helps you make better decisions faster on all data. Join us! -- Our company was founded in an unusual way; with customers and revenue from the beginning! Our growth is already ahead of some of the most successful software start-ups, and we don’t plan on slowing down. We believe our opportunity is huge. Every large company in the world suffers from a data silo problem. Traditional data warehouse products approach the problem with old solutions that breed inefficiency and ultimately can’t help business analysts run fast analytics on all their data. This prevents the business from making better decisions to improve their company’s performance. Starburst provides a modern solution that addresses these data silo & speed of access problems. Starburst helps enterprises harness the value of Trino, the fastest distributed query engine available today, by adding the tools and 24x7 support that meet the needs for big data access at scale. Ultimately, Starburst helps organizations run analytics anywhere to make better business decisions. We’re building a team of all-stars: engineers, customer success, sales, and marketing pros who are at the top of their game. If this sounds like you, check out our open roles: starburst.io/careers
Similar Research roles
