Description
The CoCounsel Agent Context team at Thomson Reuters is seeking a Staff Software Engineer to set the technical direction for Content Tools , purpose-built APIs that give AI agents precise, governed access to proprietary legal content across various international jurisdictions.
This is a high-leverage role at the intersection of API design, information retrieval, and agentic systems. The successful candidate will define how Content Tools are designed, evaluated, and operated, and set the patterns that every engineer on this team and on contributing partner teams builds against.
Content Tool Architecture & API Ownership
- Set the technical direction for the Content Tools catalog: define design patterns, schema templates, and contribution standards.
- Drive an API-first, contract-driven approach: every tool ships with a versioned contract, schema, and ownership metadata.
- Architect the retrieval and search layer behind the catalog , relevance and ranking quality on the team’s Vespa-based search platform.
- Define the agent invocation model for the catalog: clean tool boundaries exposed over MCP (Model Context Protocol).
- Build and own the shared development and testing infrastructure , common libraries, scaffolding generators, mock services, and local environments.
Verified Spec-Driven Development & Evaluation
- Own verified spec-driven development as a team-wide standard: define how acceptance criteria and evaluation datasets are written before implementation.
- Treat evaluation as foundational infrastructure the team is still maturing: assess current coverage across tool families.
- Define how offline grading pipelines and online signals combine into a continuous, trustworthy quality picture for every tool in production.
Reliability & Operations
- Take full operational responsibility for what you and your area own , you built it, you own it, you run it.
- Lead incident response for high-severity issues, write thorough post-mortems, and drive systematic fixes that prevent recurrence.
- Build the observability that makes reliability visible , including trace-level instrumentation for agentic retrieval paths.
- Own performance and cost strategy for the tool layer: capacity planning, caching, and rate limiting.
Technical Leadership & Governance
- Function as the technical authority other engineers and partner teams turn to for Content Tools API, evaluation, and architecture decisions.
- Multiply the team: develop Senior engineers through architecture guidance, design pairing, and constructive review.
- Build durable relationships with the teams that depend on you , CoCounsel Engineering, TR Labs, and product owners.
- Establish team-wide AI-assisted development patterns and model them visibly.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
- 8+ years of software engineering experience with demonstrated progression to staff-level or equivalent technical leadership.
- Mastery of Python and strong fundamentals across API design, testing strategy, system design, and security architecture.
- Track record of designing and operating API-first systems consumed by multiple teams.
- Working fluency with information-retrieval concepts.
- Demonstrated experience designing or owning evaluation frameworks for retrieval or LLM systems.
- Proven reliability ownership at the system level.
- Demonstrated security and access-control practice.
- Fluency with AI-assisted development tools.
- Strong communication: explain complex retrieval and architecture concepts to technical and non-technical audiences.
Nice to Have
- Experience building tools or APIs for agentic AI systems.
- Background in legal technology, knowledge management, or other high-stakes information domains.
- Hands-on experience operating search and retrieval engines.
- Experience operationalizing tooling for LLM-powered workflows.
- Experience establishing contribution governance for a platform built on by multiple teams.
- Familiarity with content licensing and policy-based entitlements in multi-tenant environments.
- Working understanding of infrastructure-as-code and API gateways.