Staff Software Engineer – AI Platform

About the role

Thomson Reuters is building the AI platform that will power the next decade of tax, accounting and audit products, including CoCounsel Audit, a suite of AI-native products used by accountants on real client work every day. As a Lead Software Engineer (Staff Engineer), you will own core backend and AI orchestration systems that turn frontier models into reliable, production-grade workflows at scale. This role is for the CoCounsel for Audit team, formed from the recent acquisition of the startup Materia.

Technical leadership and cross-functional influence

• Lead multi-quarter initiatives that cut across AI, product, and infra (e.g., a new orchestration layer, a low-latency retrieval system, or a unified knowledge base).
• Mentor senior and mid-level engineers, raising the bar on system design, code quality, and AI integration practices across the org.
• Help shape the team’s roadmap, technical strategy, and engineering culture – from experimentation practices to testing, rollout, and postmortems.

Design and own AI-first backend systems

• Provide your technical POV on architecting and implementing backend services (Python, FastAPI, PostgreSQL, AWS, Vercel) that power generative AI agents, complex workflows (e.g., tax filing, advisory, audit), and document-centric experiences.
• Build and evolve AI orchestration: routing, tool calling, MCP servers, multi-step workflows, safety and guardrails, and robust error handling around third-party LLMs (OpenAI, Anthropic, and others).
• Scale, reliability, and performance Design for high-throughput, low-latency AI workloads: caching, queuing, rate-limiting, model failover, and cost/performance trade-offs.
• Work with large-scale data: millions of documents, retrieval and search, vector stores, and indexing strategies tailored to tax and accounting use cases.
• Establish and refine SLOs, observability, and incident response for AI systems that must be correct, auditable, and trustworthy in professional workflows.

What You'll Do

• Shape the team's AI platform and patterns: Define patterns for building MCP servers, designing agents, novel uses of LLMs, experimentation, and scalable infrastructure.
• Shape the platform integration strategy across new and existing Thomson Reuters audit systems to provide world-class content and solutions for our customers.
• Join a tight group of senior engineers and researchers shipping quickly, with direct access to product leadership and customers.
• Think ownership of a startup with the runway of a public company.
• Enjoy and thrive at setting technical direction, mentoring senior engineers, and spending most of your time in the code and architecture of AI systems.