Senior Software Engineer - AI, CoCounsel FDE
thomson reutersColumbia (SC)
Senior Software Engineer - AI, CoCounsel FDE
Posted today
thomson reutersColumbia (SC)
SENIORITY
Lead
About the role
Overview:
In this role you design, build, and deploy production-grade AI solutions for law firms and corporate legal departments. You work with a cross-functional team to translate complex legal workflows into scalable AI pipelines that meet high-trust standards. You own the end-to-end delivery, from discovery and design to deployment and monitoring, shaping how legal professionals use AI in practice. This is a hands-on, client-facing engineering role at the frontier of legal AI, with a strong impact on the world’s leading professionals. Compensation / Benefits Hybrid Work Model Flex My Way with remote options Career development and Grow My Way Industry competitive benefits Mental health days and wellbeing programs Social Impact and volunteering opportunities
Responsibilities:
Design and implement AI-powered solutions for law firm and corporate workflows (contract review, litigation support, discovery automation, regulatory analysis) Work within architectural frameworks to build scalable, secure AI systems Architect RAG pipelines, custom AI agents, and multi-component systems with enterprise integrations Build and configure multi-step agentic workflows using CoCounsel, Westlaw, Practical Law, and third-party APIs Implement Agent-to-Agent (A2A) workflows and MCP integrations for interoperability Design and deploy bespoke automation pipelines and integration scripts for customer use cases Implement MLOps and LLMOps for production-grade AI deployments Establish observability (monitoring, logging, tracing) to track performance and health in production Contribute to model evaluation, benchmarks, and red-teaming grounded in legal workflows Ensure compliance with ethical AI principles, data protection, and security requirements Participate in technical discovery and prototype early-stage solutions for clients Translate legal workflows into engineering tasks and concrete implementation plans Demonstrate and validate solutions to clients and legal professionals Collaborate with AI engineers and architects to share knowledge and improve delivery
Key requirements:
5+ years in software engineering with strong system design and distributed architectures At least 2 years building and deploying AI/ML solutions in production (LLM-powered) Proficiency with LangChain, LangGraph, PydanticAI, or AutoGen; strong understanding of RAG and vector databases Experience with MCP and A2A workflows Strong Python (FastAPI preferred) and RESTful/async architectures Cloud experience (AWS/Azure/GCP) and IaC (Terraform, CDK) Observability stacks (Datadog, Grafana, Prometheus) Experience with AI evaluation platforms (LangSmith, Langfuse, Braintrust, Weights & Biases) Secure API development (OAuth 2.0, OpenID Connect, JWT) Strong prompt engineering skills for domain tasks Experience with AI-assisted development tools (Claude Code, Cursor, GitHub Copilot) Excellent communication with engineers and non-technical stakeholders Ability to work independently in client-facing workshops and discovery excellent communication client-facing diplomacy ability to navigate ambiguity LLM-powered applications MCP and A2A interoperability RAG architectures
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.