Lead Research Engineer, Search & Retrieval

Thomson Reuters•Frisco, NY

7d•Hybrid

About The Position

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.

Requirements

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

Nice To Haves

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

Responsibilities

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.