Senior AI Engineer – Agentic Workflows

About the Role Senior AI Engineer – Agentic Workflows. Build skills, tools, and agents powering our most advanced products incorporating generative AI, and bring them together into reliable, production-ready workflows. You will work with business and product teams to translate high-level problems into structured agentic workflows and production-ready solutions, design multi-step agentic systems using LangGraph, and integrate leading LLM providers. You may work with Claude Code and similar tools to accelerate delivery and improve code quality, while establishing strong evaluation practices to measure quality, reliability, and cost from design through deployment. What You'll Do

• Design end-to-end agentic workflows (e.g., with LangGraph) to solve complex problems.
• Translate business needs into structured, scalable AI solutions.
• Build and compose reusable skills, tools, and agents.
• Choose the right approach (skill, tool, agent, workflow) for performance and maintainability.
• Integrate multiple LLMs, optimizing cost, speed, and quality.
• Improve performance via prompt design, token use, and inference efficiency.
• Define evaluations, metrics, and guardrails to ensure quality and reliability.
• Structure and validate data using typed schemas (e.g., Pydantic).
• Implement observability, logging, and debugging tools.
• Leverage AI assistants to accelerate development.
• Collaborate cross-functionally to deliver impactful AI solutions. What We're Looking For
• 5+ years Python development with strong software engineering fundamentals
• Hands-on experience building production systems with Large Language Models
• High ownership & proactive communication: Delivers assigned outcomes autonomously, keeping progress visible and proactively surfacing blockers, changes in approach, and trade-offs—seeking input early when needed
• Proven experience with LangGraph or similar agentic frameworks (LangChain, other orchestration frameworks acceptable)
• Strong understanding of evaluation methodologies for LLM/agent quality (datasets, metrics, human review, regression testing)
• Ability to reason about when to build a skill vs tool vs agent vs workflow, with clear trade-offs
• Proven ability to decompose complex, ambiguous business problems into scalable technical solutions, from high-level requirements to detailed design. Nice to Have
• Comfort using AI assistants (e.g., Claude Code) as part of the daily engineering workflow
• Familiarity with LLM observability tools (Langfuse, LangSmith, etc.)
• Background with vector databases and RAG patterns
• Understanding of cost optimisation and token accounting in LLM systems
• Production experience with async Python