Senior AI Engineer

Pillsbury Winthrop Shaw Pittman LLP • Nashville, TN

3d • $170,000 - $200,000 • Onsite

About The Position

The Senior AI Engineer is responsible for designing, developing, deploying, and continuously improving production AI agents and agentic workflows that support attorneys, practice groups, and Firmwide Department teams across the Firm. This role translates complex business needs into reliable AI enabled solutions that combine language models, enterprise tools, governed data, workflow automation, and appropriate human review. Working primarily within Azure Databricks and/or Azure AI Studio with native Azure services, the Senior AI Engineer will develop solutions using technologies such as n8n, LangGraph, Python, and enterprise APIs. The position will maintain a strong hands-on development focus while also providing technical guidance, code review, mentoring, and training to AI Engineers and helping establish engineering standards and best practices. The Senior AI Engineer will partner closely with the department leadership, AI Engineers, Data Architects, DevOps teams, and business stakeholders to deliver secure, scalable, and production ready AI solutions.

Requirements

• Demonstrated experience personally designing, developing, deploying, and supporting production AI agents, agentic applications, or tool-enabled large language model (LLM) workflows.
• Strong Python development skills and working knowledge of SQL, APIs, automated testing, version control, code review, and maintainable software integration practices.
• Hands-on experience with LangGraph or a comparable framework used to develop stateful, multi-step AI agents.
• Experience with n8n or a comparable workflow automation platform and the ability to develop and support solutions that combine workflow automation with custom agent services.
• Hands-on experience delivering AI solutions using Azure Databricks, Azure AI Studio, and/or native Microsoft Azure services, including model access, application deployment, and integration with governed enterprise data.
• Strong understanding of agent architecture and workflow design, including tool schemas, prompt and context management, structured outputs, state transitions, memory, checkpointing, stopping conditions, and human review.
• Experience designing integrations using APIs, webhooks, and asynchronous execution, including authentication, rate limits, retries, error handling, and idempotency.
• Experience implementing retrieval-augmented generation (RAG) and governed data access, including retrieval filtering, source permissions, citations, and validation of retrieved information.
• Experience developing evaluation datasets, automated tests, and regression testing processes and using agent traces and failure analysis to improve solution performance.
• Understanding of AI application security and reliability practices, including authorization, credential protection, sensitive information handling, constrained tool access, recoverable workflows, and appropriate human controls.
• Experience with production software delivery practices, including versioning, environment configuration, automated testing, observability, monitoring, and rollback procedures.
• Demonstrated ability to translate ambiguous or complex business requirements into practical technical solutions and clearly communicate technical considerations and tradeoffs to technical and non-technical stakeholders.
• Demonstrated ability to mentor and train other engineers, conduct effective code reviews, and contribute to technical standards and best practices while maintaining significant hands-on development responsibilities.

Nice To Haves

• Production experience using both n8n and LangGraph, particularly solutions combining workflow automation with custom Python-based agent services.
• Experience deploying agents through Azure Databricks and using Lakebase or similar technologies for persistent agent state, checkpoints, and memory.
• Experience with AI evaluation and observability tools such as MLflow, LangSmith, or comparable platforms.
• Experience developing Model Context Protocol (MCP) servers, reusable agent tools, or integrations connecting AI solutions with enterprise systems and governed data.
• Experience with multi-agent architectures, model routing, advanced retrieval techniques, and other agentic design patterns.
• Working knowledge of JavaScript or TypeScript for custom integrations and lightweight application interfaces.
• Experience developing user interfaces that provide visibility into agent progress, source citations, approval workflows, and user feedback.
• Experience delivering AI or technology solutions directly with business users in legal services, professional services, or other environments involving sensitive information and complex workflows.

Responsibilities

• Partner with attorneys, practice groups, and Firmwide teams to understand existing workflows, identify opportunities for AI-enabled solutions, and define technical requirements, acceptance criteria, and appropriate boundaries for automation and human review.
• Design, build, deploy, and maintain production AI agents and agentic workflows using n8n, LangGraph, Python, enterprise APIs, and related technologies.
• Develop n8n workflows incorporating triggers, webhooks, AI Agent nodes, enterprise connectors, reusable sub-workflows, custom code, secure credential management, and appropriate error handling.
• Build stateful LangGraph workflows incorporating tool calling, conditional routing, checkpoints, persistent state, stopping conditions, recovery mechanisms, and human approval steps.
• Design prompts, context assembly, structured outputs, retrieval-augmented generation (RAG), and model selection strategies based on defined quality, latency, cost, and business requirements.
• Develop reusable agent tools, APIs, and integrations that enable agents to retrieve information and perform authorized actions securely across enterprise systems.
• Partner with the Data Architect to implement governed and permission-aware data access, retrieval, persistent state, and memory while maintaining source traceability and appropriate user and matter-level access controls.
• Develop evaluation datasets, automated tests, and regression testing processes in partnership with domain experts to assess agent behavior, retrieval quality, tool-use accuracy, task completion, groundedness, latency, and cost.
• Analyze agent traces, tool calls, workflow outcomes, and failure patterns using evaluation and observability tools to troubleshoot issues and continuously improve solution performance.
• Incorporate appropriate security and reliability controls, including input and output validation, authorization, credential protection, retries, timeouts, stopping conditions, recovery procedures, and escalation paths.
• Test solutions for risks such as prompt injection, inappropriate tool use, unauthorized data access, and data leakage, incorporating human approval for consequential actions where appropriate.
• Partner with DevOps teams to support application deployment, environment configuration, secrets management, monitoring, release management, observability, and rollback processes across Azure environments.
• Maintain ownership of the production performance, troubleshooting, maintenance, and continuous improvement of assigned AI agents and workflows.
• Mentor and train AI Engineers through technical guidance, pairing, code reviews, and practical learning sessions.
• Establish, document, and promote engineering best practices related to agent architecture, workflow development, evaluation, testing, security, observability, and production delivery.

Benefits

• The expected salary range for this position is $170,000 - $200,000. Final compensation will be determined based on several factors, including but not limited to, relevant experience, qualifications, skill set, and geographic location.
• If you require an accommodation in order to apply for a position, please contact us at [email protected].

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed