Senior AI Engineer

We are seeking a Senior AI Engineer to lead the design and development of AI-powered accelerators that streamline and automate complex business workflows. This role centres on building reliable, production-grade Agentic systems and orchestration frameworks that improve speed, quality, and reusability across delivery and modernisation initiatives. The ideal candidate combines strong hands-on engineering capability with architectural leadership, a Forward Deployment mindset, and a passion for enabling client teams through shared accelerators, assets, and patterns.

• Design, build, and maintain AI accelerators that enhance productivity and reduce delivery effort across complex business workflows.
  

• Develop Agentic and workflow-automation solutions including multi-agent orchestration, task routing, supervisory agents, and tool-use pipelines.
  

• Implement robust context-management strategies including retrieval pipelines, memory stores, episodic context, and session-state control.
  

• Architect reliable production systems with evaluation loops, telemetry, failure-handling, and safety/guardrail patterns.
  

Platform Engineering & Reuse

• Build reusable accelerator frameworks adaptable across multiple client and delivery contexts.
  

• Establish development standards, reference implementations, and reusable patterns that compress delivery timelines and eliminate guesswork.
  

• Partner with engineering and delivery teams to adapt accelerators to live projects and real-world scenarios.
  

• Contribute to documentation, training materials, and onboarding guidance for accelerator adoption across teams.
  

Technical Leadership

• Provide architectural guidance, mentorship, and code reviews for junior and mid-level engineers.
  

• Collaborate with product and delivery stakeholders to translate business workflows into automatable, scalable system designs.
  

• Advocate for reusable, forward-compatible design patterns and a culture of experimentation, evidence-based iteration, and shared learning.
  

Forward Deployment Engineering

• Embed directly with GCC client teams to deploy, configure, and operationalise AI accelerators in integration environments.
  

• Act as the technical bridge between Odyssey's core platform and client-side implementation — adapting accelerators to each GCC's toolchain, data landscape, and workflow context.
  

• Diagnose integration friction points in real-world deployments and feed learnings back into the core accelerator roadmap.
  

• Train and enable client engineers to own and extend accelerators independently, reducing long-term dependency on central platform support.
  

• Collaborate with BOT's delivery and programme management teams to ensure AI accelerators are adopted with measurable impact — tracking time-to-value, usage quality, and reuse rates across engagements.
  

Requirements

Experience

• 4+ years of professional software engineering experience, with at least 2–3 years in applied AI / LLM systems.
  

• Experience in consulting, platform engineering, or accelerator-style reusable asset development.
  

• Prior involvement in data-migration, modernisation, or analytics engineering programmes is a strong plus.
  

• Demonstrated experience in a Forward Deployment, Solutions Engineering, or embedded client-facing technical role is highly desirable.
  

LLM & Agentic Systems

• Strong expertise in LLM-based application development using frameworks such as LangChain, LangGraph, Semantic Kernel, or custom orchestration.
  

• Proven experience with Agentic design patterns including:
  

• Multi-step task planning & decomposition
  

• Tool-calling / API-driven agents
  

• Workflow graphs & supervisory agents
  

• Long-running task coordination
  

Claude Code Expertise

• Hands-on proficiency with Claude Code — Anthropic's Agentic coding tool — to accelerate development of AI-powered systems and accelerators.
  

• Ability to leverage Claude Code for end-to-end engineering tasks: scaffolding Agentic pipelines, writing and reviewing complex code, debugging production issues, and iterating rapidly on accelerator builds.
  

• Experience using Claude Code in team and enterprise environments, including MCP (Model Context Protocol) server integrations to connect Claude Code with internal tools, data sources, and workflows.
  

• Capability to train and guide other engineers on effective Claude Code usage patterns — maximising output quality, context management, and safe Agentic task execution.
  

Context & Retrieval Design

• Deep familiarity with RAG pipelines, embedding strategies, and retrieval quality evaluation.
  

• Experience with grounding, prompt-context isolation, vector stores, and document indexing at scale.
  

Software Engineering Fundamentals

• Python (primary) — testing, packaging, dependency management, and CI/CD deployment patterns.
  

• Architectural design and code quality best-practices for production AI systems.
  

• Experience designing observability and evaluation loops for AI workflows — telemetry, metrics, regression testing, and drift tracking.
  

• Integration experience with data platforms/warehouses, metadata systems, workflow tools, and REST/Microservices architectures.