Senior Software Engineer – AI

Thomson Reuters · United States of America, Frisco, Texas · hybrid Are you a hands-on AI engineer who wants to build the next generation of legal AI solutions from the ground up? Do you thrive taking an architectural blueprint and turning it into a robust, production-ready system that lawyers actually rely on? Join Thomson Reuters' CoCounsel Forward Deployed Engineering team , a high-impact group working at the frontier of legal AI, where your code ships directly to law firms and corporate legal departments and your engineering shapes how the world's leading legal professionals work. As a Senior Software Engineer – AI, you will work side-by-side with the AI Solutions Architect, Senior Legal AI Engineers, and fellow AI engineers to design, build, and deploy bespoke AI solutions from zero to one for law firms and corporate legal departments. Key Responsibilities Solution Design & Engineering Design and implement AI-powered solutions tailored to law firm and corporate legal workflows, including contract review, litigation support, discovery automation, and regulatory analysis. Work within architectural frameworks set by the AI Solutions Architect to build scalable, secure, and maintainable AI systems. Architect RAG pipelines, custom AI agents, and multi-component systems that integrate securely into client environments, including document management systems and enterprise platforms. Build and configure multi-step agentic workflows leveraging CoCounsel, Westlaw, and Practical Law capabilities, as well as third-party AI APIs and enterprise integrations. Implement Agent-to-Agent (A2A) workflows and Model Context Protocol (MCP) integrations to enable interoperability between AI agents and external tools, data sources, and enterprise systems. Design and deploy bespoke automation pipelines and integration scripts tailored to each customer's use case. Implement MLOps and LLMOps practices to support scalable, maintainable deployment of AI solutions in production. Observability, Quality & Trust Implement monitoring, logging, and tracing solutions to track LLM performance, latency, token usage, and system health in production. Leverage AI evaluation platforms (such as LangSmith, Braintrust, or Weights & Biases) to assess model outputs, track evaluation metrics over time, and surface quality regressions across deployed solutions. Contribute to LLM evaluation efforts , assessing model outputs for accuracy, citation quality, hallucination risk, and fitness for high-stakes legal use , in partnership with the AI Solutions Architect and product team. Develop and maintain evaluation benchmarks, test suites, and red-teaming protocols grounded in real legal workflows, and translate findings into structured input for product and engineering roadmaps. Ensure all solutions comply with ethical AI principles, data protection standards, and enterprise security requirements. Discovery & Client Engagement Participate in technical discovery on client engagements , contributing to use case scoping, solution design discussions, and early-stage prototyping. Translate complex legal workflows, pain points, and client goals into concrete engineering tasks and implementation plans. Conduct technical demonstrations and early-stage prototyping to support solution design and client confidence. Build trust with legal professionals through fluency in legal terminology, workflows, and the real-world constraints of legal practice. Work directly with legal SMEs to understand their professional reasoning and judgement, and translate that domain knowledge into AI pipeline design, evaluation criteria, and benchmarks. Technical Contribution & Collaboration Collaborate closely with Senior Legal AI Engineers, the AI Solutions Architect, and fellow AI engineers to deliver high-quality solutions across engagements. Contribute to team knowledge-sharing, internal documentation, and reusable solution templates that accelerate delivery across the team. Evaluate and prototype cutting-