Senior Agentic AI Engineer

Senior Agentic AI Engineer. A fast-growing, engineering-led AI consultancy with industry recognised entrepreneur leadership is hiring Senior Agentic AI Engineers to design, build and run production AI systems for existing enterprise client base in retail, pharmaceutical, financial services and FMCG / Consumer Products.

Permanent, remote first with some trips to office and clients.

Our client has more enterprise AI work than it can currently staff and is building out its permanent engineering team. You will be the hands-on engineer in a small, senior client delivery team, working alongside a consultant and a delivery lead.

Together you take a loosely defined business problem through to a working, production-grade AI system that is safe, observable and maintainable. Evaluation, guardrails and monitoring are built in from day one. You will also help shape engineering standards and the reusable patterns the wider team builds on.

This is a senior individual contributor role for someone who still loves building, not a step into management.

• Design and build LLM applications using modern orchestration patterns, prompt frameworks and evaluation loops
• Build multi-agent systems covering planning, delegation, tool use, safety constraints and monitoring
• Build retrieval pipelines: embeddings, vector stores, RAG and semantic search
• Apply knowledge modelling (ontologies, knowledge graphs) to improve reasoning and data alignment
• Integrate AI systems with enterprise platforms through APIs, tools and connectors
• Set the technical direction on your engagements and shape the architecture of client solutions

• Turn ambiguous business needs into clear, practical engineering approaches
• Assess feasibility across data, systems and architecture
• Help shape use cases with consultants and explain clearly how a solution will work
• Work with client domain experts to understand edge cases and operational requirements
• Produce lightweight technical documentation, diagrams and decision records

• Implement evaluation frameworks and safety checks across model and agent behaviour
• Build monitoring, logging, tracing and incident-handling patterns
• Apply governance, risk and compliance principles to AI deployments
• Support release cycles, environments and operational readiness
• Own reliability, reproducibility and performance benchmarks

• Turn what you build into reusable agent patterns, templates and starter kits
• Share new research, frameworks and techniques with colleagues
• Coach peers and influence coding standards and architectural practice

• 6 to 8 years in software or application engineering, AI engineering or applied data engineering
• Strong hands-on experience with LLMs, embeddings, RAG, retrieval stacks and vector stores
• Practical experience building multi-agent systems, agent orchestration or MCP-style tool patterns
• Strong Python, with a track record of production-grade workflows
• Experience with at least one cloud AI ecosystem:
  Azure OpenAI, Google Vertex AI, AWS Bedrock or Anthropic
• Working knowledge of semantic modelling, ontologies or knowledge graphs
• Ability to turn open-ended business problems into working prototypes quickly
• Comfortable in client-facing delivery, ideally within a consultancy
• Domain experience in life sciences, pharma or healthcare, FMCG or retail, insurance, or banking and financial services
• Deeper ontology or knowledge graph expertise
• Experience with LLM evaluation and observability tooling
• Strong engineers from non-AI backgrounds who have moved quickly into agentic AI and can show what they have built are very welcome

• Senior and genuinely hands-on, with…