Lead Research Engineer, Search & Retrieval

About the Role Retrieval is the ceiling on everything above it. An agent working a legal, tax, or regulatory question is only as good as the evidence handed to it, whether it can find the controlling authority in a corpus of millions of documents, weigh sources that conflict, and be honest about what it doesn't have. Every higher-order capability we ship depends on retrieval being trustworthy first. This role, in TR Labs, owns the engineering behind that layer: next-generation search and retrieval serving both traditional search experiences and agentic AI workflows over large collections of legal, tax, and regulatory content. Multiple product teams depend on what it delivers. What makes this research engineering rather than software engineering is that the answer isn't known when you start. Whether a different ranking model, a hybrid retrieval strategy, a new chunking scheme, or an agentic retrieval loop actually makes results better is an empirical question — and an easy one to get wrong, because a metric moving is not the same as retrieval improving. You form the hypothesis, isolate the variable, read the numbers honestly, and kill the idea when the data says to. Then you do the part many researchers don't: make the winning version production-grade, ship it, and keep it healthy. You will work shoulder-to-shoulder with applied scientists, building on their models and research directions and feeding production evidence back into the science. As a Lead you own end-to-end delivery, you deliver through the people around you, and you are the person we rely on to know the details, look around corners, and tell us early when something is going sideways. About You You are unusually rigorous with evidence. You reach for a baseline, an ablation, and a control before you trust a result, and you have the taste to know which experiments are worth running and which are not. You have launched search systems, not just built them, but operated them, scaled them, debugged them at 2am, and measured whether they actually made retrieval better. You build with AI tooling rather than around it, and you bring the same skepticism to what a coding agent hands you as to what an experiment tells you. You don't wait to be handed a problem. Given a messy project, you can work out what the most impactful next thing to do is and go do it. You can explain your work to engineers, scientists, and product stakeholders alike: defend a design choice, and update on evidence when someone shows you a better one. What You'll Do Own end-to-end delivery of significant search and retrieval projects, accountable for the outcome, the quality and timeline, and the system once it is live Act as technical lead for a squad of 3–5 engineers: set direction, break down the work, review designs and code, and unblock the team Partner closely with applied scientists, build on their models, ranking approaches, and research directions, and feed production evidence back into the science Run the exploration → POC → proof of value → productionization loop, and decide what to try next, including what not to try Design and build retrieval architectures, ingestion and indexing pipelines, and ranking and re-ranking systems on OpenSearch and Vespa Build the retrieval infrastructure that agentic AI workflows depend on, and the search agents themselves: tool-facing retrieval APIs, agentic query planning and multi-step retrieval, RAG pipelines, hybrid and semantic retrieval, and query understanding Build evaluation that actually discriminates — offline relevance harnesses, golden and labeled sets, online A/B tests, and end-to-end agent quality measurement designed to separate real improvement from a number that happened to move, and to keep discriminating as the models get stronger Diagnose retrieval and agent quality failures: why is this result wrong, which stage of the pipeline caused it, and what does that imply about the design Build and operate production APIs and backend services on AWS, with the performance, reliability, and cost characteristics that mission-critical systems require Identify and communicate risk to timelines and architecture early and clearly, to peers and to senior stakeholders Influence architecture decisions beyond your own squad through design review, alignment with partner teams, and mentorship. Minimum Qualifications Bachelor's or Master's in Computer Science, Engineering, or a related field ~7+ years building production software, including search, retrieval, or ranking systems you shipped and then owned — launched, scaled, and maintained, not just prototyped Proven track record leading technical projects and delivering through other engineers, and influencing architecture decisions across teams Deep hands-on production expertise in OpenSearch or Vespa (or comparable depth in Elasticsearch, Solr, or Lucene, with the ability to ramp on ours) rather than only consuming a vector database or a retrieval API Rigor with evidence: designing search experiments, relevance and ranking metrics, offline evaluation harnesses, online A/B measurement — and the discipline to know when a result is real Outstanding software engineering in Python, across the stack from ingestion pipelines to retrieval services to evaluation infrastructure AI-native development: agentic coding tools are a routine part of how you build, and you have judgment about where they make you faster and where their output needs checking before it ships Designing, operating, and scaling production APIs and large-scale distributed systems on AWS, including performance optimization at scale Information retrieval fundamentals: indexing and ingestion at large corpus scale, vector search, embeddings, semantic and hybrid retrieval, and RAG infrastructure built for production use Track record of collaborating with applied scientists or ML practitioners and productionizing their models and approaches Preferred Qualifications Search relevance and ranking depth: query understanding, learning-to-rank, LLM-based ranking or re-ranking LLM-as-judge or model-assisted relevance evaluation, and evaluating open-ended or knowledge-intensive LLM behavior Retrieval systems and search agents purpose-built for agentic AI workflows Kafka, event-driven architectures, and large-scale data pipelines ML infrastructure, embedding pipelines, and vector databases Operating mission-critical production systems with meaningful SLAs Experience with legal, regulatory, tax, scientific, or other text-heavy domains Self-service platform capabilities consumed by internal product teams #LI-TH1 This posting is for proactive recruitment purposes and may be used to fill current openings or future vacancies within our organization. What’s in it For You? Hybrid Work Model: We’ve adopted a flexible hybrid working environment for our office-based roles while delivering a seamless experience that is digitally and physically connected. Flexibility & Work-Life Balance: Flex My Way is a set of supportive workplace policies designed to help manage personal and professional responsibilities, whether caring for family, giving back to the community, or finding time to refresh and reset. This builds upon our flexible work arrangements, including work from anywhere for up to 8 weeks per year, empowering employees to achieve a better work-life balance. Career Development and Growth: By fostering a culture of continuous learning and skill development, we prepare our talent to tackle tomorrow’s challenges and deliver real-world solutions. Our Grow My Way programming and skills-first approach ensures you have the tools and knowledge to grow, lead, and thrive in an AI-enabled future. Industry Competitive Benefits: We offer comprehensive benefit plans to include flexible vacation, two company-wide Mental Health Days off, access to the Headspace app, retirement savings, tuition reimbursement, employee incentive programs, and resources for mental, physical, and financial wellbeing. Culture: Gl