Principal Engineer, CoCounsel

Principal Software Engineer –   CoCounsel   CoCounsel   is our most advanced AI offering to date – combining generative and agentic AI capabilities to help legal professionals move beyond prompting and start delegating.  As a Principal Software Engineer, you will set the technical direction for the backend, AI orchestration, and identity systems that turn frontier models into reliable, secure, production-grade workflows that attorneys, in-house legal departments, and government agencies trust on real client matters every day.   This role sits at the heart of the   CoCounsel   Legal engineering organization, partnering closely with AI/ML engineers, researchers, product, and our identity and platform teams to deliver world-class legal content and AI experiences at scale.   About the role:   In this opportunity as a Principal Software Engineer, you will: Participate in s hap ing   the company’s AI platform and patterns:   Define patterns for building MCP servers, designing agents, novel uses of LLMs, experimentation, and scalable infrastructure. Your decisions will influence multiple product lines, not just a single feature.   Work at real production scale: Build and evolve systems that operate over millions of documents, complex and ever-changing law, privileged client data, and thousands of concurrent AI interactions from professionals doing time-sensitive work.   Considering implications to   cloud costs, optimizations, etc.   Small team, big surface area:   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.   Technical leadership and cross-functional influence :   Lead   and/or design   initiatives that cut across AI, product, identity, and infrastructure .    Mentor staff and senior engineers, raising the bar on   AI integration practices,   system design, code quality,   and   security across the org.     Be the expert in new model capabilities, collaborating closely with AI/ML engineers, researchers, designers, and PMs to translate industry improvements into reliable, user-facing workflows that legal professionals trust.   Help shape the team’s roadmap, technical strategy, and engineering culture – from experimentation practices to testing, rollout, and postmortems.     Help define and lead the platform integration strategy across new and existing Thomson Reuters legal systems to deliver world-class content and solutions for our customers.   Identity, access, and trust :   Define how autonomous agents act on a user’s behalf safely: scoped delegation, least-privilege service identities, secrets management, and consistent enforcement of entitlements across documents, matters, and content repositories.     Partner with security, platform, and compliance teams on multi-tenancy isolation, data residency, privilege protection, and the audit trails that legal and government customers require.     Consider the design and evolution of authentication and authorization across   CoCounsel   Legal – SSO/federation (SAML, OIDC, OAuth 2.0), token and session management, and fine-grained, role- and attribute-based access control (RBAC/ABAC).   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 legal use cases.   Establish and refine SLOs, observability, and incident response for AI systems that must be correct, auditable, and trustworthy in professional legal workflows.   ​ About You:   You are a fit for the position of Principal Software Engineer if your background includes:   Bachelor’s Degree in Computer Science , Computer Engineering, a related field, or equivalent experience.   Demonstrated experience building with AI – LLMs, agents, and retrieval – and a strong point of view on what “AI-native” software should look like.   Proven track record owning large, complex projects end-to-end: architecture, execution, rollout, and long-term operation.   Deep Python expertise and experience with production systems using frameworks like   FastAPI   (or similar), relational databases (PostgreSQL or equivalent), and a major cloud provider (AWS preferred).   Strong background in distributed systems: data modeling, API contracts, observability, resilience patterns, and performance tuning under load.   Hands-on experience with identity and access management – designing or integrating authentication and authorization at scale (SSO, SAML, OIDC, OAuth 2.0, RBAC/ABAC, token/session management, or comparable IAM systems).   Excellent communication skills and the ability to partner with product, design, security, and ML teams in a fast-moving environment.   Preferred Skills & Experience:   Hands-on experience designing and operating agentic systems in production – tool calling, MCP servers, multi-step workflows, and orchestration around third-party and in-house LLMs (e.g., Anthropic, OpenAI), including prompt/response management, cost controls, and safety considerations.   Experience with AI-adjacent infrastructure: vector databases, embeddings, semantic search, or custom retrieval pipelines.   Opinions and experience around automated testing, reliability, and release practices for systems with non-deterministic model behavior.   #LI-ES1 Replacement: This position is open due to an existing vacancy to support our evolving business needs. What’s in it For You? Hybrid Work Model: We’ve adopted a flexible hybrid working environment (2-3 days a week in the office depending on the role) 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 supp