Senior Agentic AI Engineer | NDA

The role

You will design and evolve a production-grade AI platform for conversational data analytics. This role involves building scalable agentic AI systems and making architectural decisions using Python.

What you will do

• Design, build, and improve agentic AI workflows for conversational analytics, data exploration, and visualization.
• Develop an extensible agentic framework with reusable tools, skills, conversation management, and client-specific configurations.
• Build secure integrations with application services and governed data sources, including sandboxed code execution.
• Contribute to the evolution of the existing LangChain-based solution toward Pydantic AI.
• Develop MCP servers and clients to enable communication and data exchange between agents and applications.
• Implement LLM evaluation, testing, observability, and security controls.
• Own AI features end to end from implementation to production release.

Required qualifications

• 6+ years of experience in software engineering, data analytics, or related fields.
• 2+ years in agentic AI engineering.
• Strong Python development skills.
• Experience building agentic AI systems using frameworks such as Pydantic AI, LangGraph, LangChain, or OpenAI Agents SDK.
• Strong understanding of agentic patterns, including tool calling, multi-step orchestration, context management, guardrails, and human-in-the-loop workflows.
• Experience with MCP (Model Context Protocol) and multi-agent or cross-application integrations.
• Experience developing AI agents for data analysis, including dataset exploration, code generation and execution, and result interpretation.
• Solid system design and architecture skills.
• Practical experience with LLM evaluation, testing, and observability (Phoenix, OpenTelemetry, or similar).
• Understanding of AI security and secure data access.
• Strong ownership, communication, and collaboration skills.
• Effective daily use of AI coding assistants (Claude Code, Codex, or similar) and validation of generated code.

Nice to have

• Hands-on experience with Pydantic AI / Pydantic AI Harness.
• Experience designing agentic foundations for software products and/or evolving existing agentic solutions.
• Familiarity with LangChain-based systems.
• Experience with data analysis technologies such as SQL, pandas, DuckDB, or Ibis.
• Familiarity with Azure OpenAI, Docker, and data visualization tools such as Plotly or Dash.
• Experience in retail, pricing, promotions analytics, or similar domains.
• Experience delivering client-facing AI products from prototype to production.
• Familiarity with React and FastAPI.

About the company

GT connects the world's best talent with product careers in the UK, USA, Canada, Germany, and the Netherlands. The client is a leading global management consultancy focused on strategy, transformation, and performance improvement.