Under the direct supervision of the Director of Practice & Business Systems, the AI Solutions Engineer is responsible for designing, building, and deploying custom applications and AI solutions for Practice Groups and Business Professionals using modern, professional software development practices. The role combines application development on the Microsoft and Azure stack with the development of AI solutions, including retrieval-augmented generation (RAG) assistants, custom Model Context Protocol (MCP) servers, and integrations with the APIs and SDKs of enterprise AI platforms.
Responsibilities:
- Design, build, test, deploy, and support custom web applications and APIs for Practice Groups and Business Professionals, leading projects from requirements through production support.
- Collaborate with Practice Groups and Business Professionals to identify opportunities to automate business processes and enhance capabilities through custom applications and AI, delivering solutions iteratively with regular stakeholder feedback.
- Collaborate with Network Systems, Information Security, and Electronic Information Governance teams to ensure all solutions comply with security, privacy, and governance standards.
- Design and maintain REST APIs and production data pipelines, applying sound SQL and data modeling practices.
- Build and ship AI solutions to production users, including RAG-based chat and knowledge assistants grounded in firm content, tool-calling agents, and, as needed, custom MCP servers.
- Integrate enterprise AI platforms (e.g., Azure OpenAI Service, AI Foundry, Copilot Studio, Anthropic) through their APIs and SDKs, and build agentic solutions with agent frameworks that integrate with enterprise services and data sources.
- Design, deploy, and operate applications and services on Azure, using CI/CD pipelines to automate build, test, security scanning, and deployment.
- Follow established software development life cycle (SDLC) methodologies and best practices, including Git-based source control, pull requests, peer code review, automated testing, and technical documentation, and contribute to team standards and reusable components.
- Use AI-assisted engineering tools to accelerate development while remaining accountable for the architecture, correctness, security, and maintainability of all code produced.
- Monitor, evaluate, and maintain deployed applications and AI solutions, tracking output quality over time along with accuracy, latency, cost, safety, reliability, and scalability, with guardrails, logging, and observability.
- Evaluate emerging AI technologies and development tools and recommend adoption strategies to improve business processes and outcomes.
Under the direct supervision of the Director of Practice & Business Systems, the AI Solutions Engineer is responsible for designing, building, and deploying custom applications and AI solutions for Practice Groups and Business Professionals using modern, professional software development practices. The role combines application development on the Microsoft and Azure stack with the development of AI solutions, including retrieval-augmented generation (RAG) assistants, custom Model Context Protocol (MCP) servers, and integrations with the APIs and SDKs of enterprise AI platforms.
Responsibilities:
- Design, build, test, deploy, and support custom web applications and APIs for Practice Groups and Business Professionals, leading projects from requirements through production support.
- Collaborate with Practice Groups and Business Professionals to identify opportunities to automate business processes and enhance capabilities through custom applications and AI, delivering solutions iteratively with regular stakeholder feedback.
- Collaborate with Network Systems, Information Security, and Electronic Information Governance teams to ensure all solutions comply with security, privacy, and governance standards.
- Design and maintain REST APIs and production data pipelines, applying sound SQL and data modeling practices.
- Build and ship AI solutions to production users, including RAG-based chat and knowledge assistants grounded in firm content, tool-calling agents, and, as needed, custom MCP servers.
- Integrate enterprise AI platforms (e.g., Azure OpenAI Service, AI Foundry, Copilot Studio, Anthropic) through their APIs and SDKs, and build agentic solutions with agent frameworks that integrate with enterprise services and data sources.
- Design, deploy, and operate applications and services on Azure, using CI/CD pipelines to automate build, test, security scanning, and deployment.
- Follow established software development life cycle (SDLC) methodologies and best practices, including Git-based source control, pull requests, peer code review, automated testing, and technical documentation, and contribute to team standards and reusable components.
- Use AI-assisted engineering tools to accelerate development while remaining accountable for the architecture, correctness, security, and maintainability of all code produced.
- Monitor, evaluate, and maintain deployed applications and AI solutions, tracking output quality over time along with accuracy, latency, cost, safety, reliability, and scalability, with guardrails, logging, and observability.
- Evaluate emerging AI technologies and development tools and recommend adoption strategies to improve business processes and outcomes.
Job Specifications:
- 5+ years of professional software engineering experience with C#, ASP.NET MVC, and React, plus expert-level Python (advanced typing, structured async concurrency, descriptors, context managers) and REST API design using FastAPI or similar.
2+ years shipping LLM-based applications to production, including tool-calling agents, RAG with vector and hybrid search, structured outputs, and ongoing quality evaluation.
Hands-on experience with an agent framework or SDK (e.g., LangGraph, Microsoft Agent Framework, Claude Agent SDK) and a clear understanding of its limits.
Strong SQL and data modeling skills, including production data pipelines on SQL Server, PostgreSQL, Snowflake, or similar.
Experience deploying and operating services on Azure (preferred) or AWS, including containers, serverless compute, managed databases, secrets, identity, networking, and infrastructure as code.
Proficiency with CI/CD pipelines and Git-based source control workflows.
Experience using AI coding assistants (e.g., Codex, Claude Code) within a professional software development framework.
Preferred: legal or other regulated industry experience (e.g., financial services).
Preferred: experience building MCP servers; LLM observability tools (Langfuse, LangSmith); fine-tuning and open-weight models (PyTorch, Hugging Face).
Attendance Requirements: On site during normal working hours and available as necessary before or after normal working hours.
Job Specifications:
- 5+ years of professional software engineering experience with C#, ASP.NET MVC, and React, plus expert-level Python (advanced typing, structured async concurrency, descriptors, context managers) and REST API design using FastAPI or similar.
2+ years shipping LLM-based applications to production, including tool-calling agents, RAG with vector and hybrid search, structured outputs, and ongoing quality evaluation.
Hands-on experience with an agent framework or SDK (e.g., LangGraph, Microsoft Agent Framework, Claude Agent SDK) and a clear understanding of its limits.
Strong SQL and data modeling skills, including production data pipelines on SQL Server, PostgreSQL, Snowflake, or similar.
Experience deploying and operating services on Azure (preferred) or AWS, including containers, serverless compute, managed databases, secrets, identity, networking, and infrastructure as code.
Proficiency with CI/CD pipelines and Git-based source control workflows.
Experience using AI coding assistants (e.g., Codex, Claude Code) within a professional software development framework.
Preferred: legal or other regulated industry experience (e.g., financial services).
Preferred: experience building MCP servers; LLM observability tools (Langfuse, LangSmith); fine-tuning and open-weight models (PyTorch, Hugging Face).
Attendance Requirements: On site during normal working hours and available as necessary before or after normal working hours.