Mid Level AI Developer

• Design and build single- and multi-agent AI workflows with planning, tool use, memory and human-in-the-loop controls
• Develop LLM applications on AWS and Azure AI platforms and recommend the appropriate platform and model for each use case
• Build RAG pipelines covering data ingestion, chunking, embeddings, vector search and enterprise-data grounding
• Integrate agents with internal systems, APIs and SaaS tools using MCP and function/tool calling
• Implement evaluation frameworks for quality, accuracy, safety and cost, including regression tests, LLM-as-judge methods and human review
• Add responsible-AI controls including prompt-injection defences, content filtering, PII handling, access control and audit logging
• Containerise and deploy services with CI/CD and infrastructure as code
• Add observability through tracing, logging, latency and token-cost monitoring
• Optimise performance, reliability and cost across models, prompts and infrastructure
• Mentor engineers, run design and code reviews, and document architectures and decisions
• Collaborate with product owners, data teams, security and architecture to take AI use cases from idea to production

• Bachelor's degree in Computer Science, Engineering or a related field (or equivalent experience)
• 3+ years of software engineering experience, with 1+ years building LLM or GenAI applications in production
• Strong Python skills, plus experience building and operating APIs and services
• Hands-on experience building agentic systems with a modern framework (for example LangGraph, LangChain, Microsoft Agent Framework / Semantic Kernel, AutoGen, Strands Agents or CrewAI)
• Production experience on at least one of AWS or Azure AI services, and working knowledge of the other
• Practical RAG experience with vector databases or search services (for example OpenSearch, Azure AI Search, pgvector or Pinecone)
• Experience with cloud fundamentals: containers (Docker, Kubernetes or serverless), networking and identity (IAM / Entra ID), and secrets management
• Experience with CI/CD, Git and infrastructure as code (Terraform, Bicep or CloudFormation)
• Understanding of LLM evaluation, prompt engineering, and safety and security risks specific to AI systems
• Strong communication skills and the ability to explain trade-offs to technical and non-technical stakeholders
• Experience with MCP servers, multi-agent protocols (for example A2A), or agent orchestration at scale
• Fine-tuning or model customization, and experience with open-source models
• Background in a regulated sector such as banking, healthcare or government
• Cloud certifications (for example AWS Certified AI Practitioner or Solutions Architect, Azure AI-102 or AZ-204, AZ-400)
• Experience with data engineering (Spark, Databricks, Fabric or Glue) and data governance