Python AI Developer (ID: UdmSCzpr)

Are you an experienced Senior GenAI & Agentic AI Developer? Would you like to play a key role in building and evolving an enterprise-grade Generative AI Platform for a leading global insurer?

This is an exciting opportunity to work at the forefront of enterprise AI, developing the core services, capabilities and integrations that will enable the secure and scalable adoption of Generative AI and Agentic technologies across a complex global organisation.

Combining strong Python backend engineering with hands-on GenAI development and DevOps expertise, you will help transform emerging AI technologies into robust, production-ready enterprise solutions.

You will work closely with platform engineers, architects and SRE teams, contributing to the design, development and operationalisation of scalable AI services in a highly regulated environment.

The ideal candidate will be technically strong, proactive and naturally curious, with practical experience developing GenAI and Agentic solutions and a passion for automation, engineering excellence and solving complex technical challenges.

Key Responsibilities

• Design, develop and maintain backend services and APIs that provide secure access to enterprise LLM capabilities.
• Build and optimise Python-based GenAI and Agentic components, including prompt orchestration, output validation and evaluation frameworks.
• Integrate LLM technologies with enterprise applications, security frameworks and observability platforms.
• Design, implement and maintain CI/CD pipelines, primarily using Azure DevOps, in line with established engineering standards.
• Collaborate with platform leads, solution architects and SRE teams to ensure the reliability, scalability and operational readiness of GenAI services.
• Support LLM benchmarking, performance evaluation, cost optimisation and experiment tracking.
• Contribute to Retrieval-Augmented Generation (RAG) implementations and enterprise data access patterns.
• Establish reusable engineering patterns, API standards and technical documentation to support wider platform adoption.
• Troubleshoot, monitor and optimise performance across distributed systems and cloud-based environments.
• Champion automation and continuous improvement to accelerate delivery and improve engineering efficiency.

Essential Skills & Experience

We are looking for candidates with a strong combination of software engineering, cloud infrastructure and practical AI development experience.

• Python & Backend Engineering
• Strong commercial experience developing and supporting production-grade Python applications and backend services.
• Experience building RESTful APIs and microservices, ideally using FastAPI.
• AWS & Cloud Technologies
• Hands-on experience with AWS services, including:
• EC2, EKS and S3
• SQS and Kinesis/Firehose
• Amazon Bedrock and AgentCore
• Generative AI & Agentic Development
• Practical understanding and experience working with Generative AI technologies and Large Language Models (LLMs).
• Experience with prompt engineering, orchestration and the complexities of handling LLM outputs.
• Knowledge of LLM evaluation, performance benchmarking and optimisation.
• Experience integrating AI capabilities into real-world applications, products or business workflows.
• DevOps & Engineering Practices
• Strong DevOps mindset with hands-on CI/CD pipeline development and automation experience.
• Understanding of observability, monitoring, logging and operational best practices.
• Knowledge of infrastructure security, authentication, secrets management, network boundaries and model access governance.
• Enterprise Environments
• Experience delivering solutions within large-scale, regulated enterprise environments.
• Understanding of secure software development practices and the challenges of deploying and managing AI services at scale.

Desirable Skills & Experience

• Experience with any of the following technologies and practices would be advantageous:
• API Management & Service Mesh: Kong API Gateway and Kong Mesh.
• GitOps & Deployment: Flux CD and GitOps-based deployment workflows.
• Infrastructure as Code: Terraform and cloud infrastructure automation.
• AI Evaluation & Security: Promptfoo, Arize, prompt red-teaming and LLM evaluation frameworks.
• Databases: SQL technologies such as MySQL and PostgreSQL, alongside NoSQL platforms including MongoDB and Cassandra.
• GenAI Architecture: Retrieval-Augmented Generation (RAG), vector databases and semantic search technologies.
• Cloud-native Development: Microservices, containerisation and Kubernetes-based architectures.

What We're Looking For

Beyond technical expertise, we're looking for someone who thrives in a fast-moving and evolving technology environment.

You will ideally demonstrate:

• Initiative: A proactive self-starter who identifies opportunities, anticipates challenges and takes ownership of solutions.
• Adaptability: Confidence working in emerging technology domains where standards and best practices are continually evolving.
• Collaboration: Strong communication skills and the ability to build trusted relationships across engineering, architecture, data and product teams.
• Curiosity: A genuine interest in exploring new GenAI and Agentic AI capabilities and applying them responsibly within an enterprise setting.
• Automation Mindset: A passion for reducing manual effort, eliminating repetitive tasks and improving delivery through automation.
• Engineering Excellence: A commitment to building secure, maintainable, scalable and reusable solutions.

What Success Looks Like

In this role, success will be measured by your ability to deliver meaningful engineering capabilities that enable the wider organisation to adopt and scale Generative AI.

You will have helped to:

• Deliver efficient, secure and reusable GenAI components into production.
• Increase engineering productivity through automation and modern DevOps practices.
• Build reliable AI services with observability, monitoring and evaluation embedded from the outset.
• Create platform capabilities that application and engineering teams actively adopt and value.
• Establish clear technical documentation, reusable patterns and streamlined onboarding for future AI use cases.

Why Join?

This is an opportunity to work on a strategically important enterprise AI platform, helping shape how Generative AI and Agentic technologies are engineered, secured and deployed at scale.

You will be part of a collaborative engineering environment where innovation, technical ownership and continuous learning are encouraged, with the opportunity to make a tangible impact on the future of enterprise AI.

Position: AI Developer (Python) - Job Type: Full-time - Salary: up to £70,000 DOE - Location: Hybrid Working/ London