AI Platform Engineering Lead - Agentic SDLC
Posted 1 day ago by Nexify Infosystems
£50 Per hour
Inside
Hybrid
London Area, United Kingdom
Summary: The Senior AI Platform Engineering Lead will design and operationalize an enterprise Agentic AI harness for end-to-end SDLC automation in .NET and Azure environments. This role requires strong software engineering and AI engineering skills to create an agent-based platform that automates key SDLC activities. The successful candidate will work closely with various stakeholders to ensure the harness meets enterprise engineering standards and is production-ready. The position is hybrid, requiring 2 to 3 days on-site in London.
Key Responsibilities:
- Design and build an AI Agentic Harness that orchestrates multiple AI agents across the SDLC.
- Integrate the harness with development tools such as GitHub Copilot, GitHub, Azure DevOps, and CI/CD platforms.
- Build agents that can generate business and technical specifications, epics, features, user stories, acceptance criteria, design decisions, and architecture decision records.
- Execute the harness to generate working .NET/C# code and create reusable patterns, templates, prompts, workflows, and agent configurations.
- Implement mechanisms for code review, quality checks, static analysis, and automated feedback.
- Ensure generated applications are deployable into Azure environments and contribute to security, compliance, and governance controls around AI-generated software delivery.
- Continuously improve the harness based on output quality, developer feedback, and delivery outcomes.
Key Skills:
- Hands-on experience with AI and Agentic Engineering, including building AI agents and multi-agent workflows.
- Experience using AI coding tools such as GitHub Copilot and designing automated workflows for SDLC activities.
- Strong experience with .NET/C# and building APIs, services, and cloud-native applications.
- Good understanding of software architecture, clean code principles, design patterns, and Test-Driven Development (TDD).
- Familiarity with test frameworks and automated testing tools within the .NET ecosystem.
- Experience with Semantic Kernel, Azure AI Foundry, Azure OpenAI, or OpenAI APIs is advantageous.
- Ability to create technical documentation, reference architectures, and engineering playbooks.
Salary (Rate): £50.00/hr
City: London
Country: United Kingdom
Working Arrangements: hybrid
IR35 Status: inside IR35
Seniority Level: Senior
Industry: IT
Title : Senior AI Platform Engineering Lead - Agentic SDLC Automation
Location : London, UK - Hybrid 2 to 3 days
Duration : 12+ Months
Rate: £400/Day
Inside IR35
1. The Role
We are looking for an experienced AI Platform Engineering Lead to design, build, and operationalise an enterprise Agentic AI Harness that enables end-to-end SDLC automation across .NET and Azure environments. The successful candidate will create an agent-based engineering platform scaffolding or harness using GitHub Copilot agents. Knowledge in frameworks such as Microsoft Agentic Framework, ADK, LangGraph, LangChain, or LangFuse isn’t mandatory, but an advantage. This harness will automate and assist key SDLC activities, including requirements generation, specification creation, story breakdown, design decision capture, task planning, test generation, code creation, test execution, infrastructure-as-code generation, and CI/CD pipeline creation. The target outcome of the harness will be production-ready .NET code deployable into an Azure cloud environment. This role is ideal for someone with strong software engineering experience, practical AI engineering skills, and a deep understanding of modern DevOps, cloud-native architecture, and enterprise-grade application delivery.
2. Tech Skills Required
The candidate should have hands-on experience with the following:
- AI and Agentic Engineering
- Experience building AI agents, multi-agent workflows, or agentic orchestration systems.
- Prompt engineering, tool calling, structured outputs, agent memory, planning, routing, and evaluation patterns
- Experience integrating LLMs with enterprise systems, repositories, APIs, and development workflows
- Understanding of AI observability, tracing, evaluation, guardrails, and feedback loops
- Awareness of frameworks such as Microsoft Agentic Framework, ADK, LangGraph, LangChain or LangFuse, will be beneficial but not mandatory
- SDLC Automation and Developer Productivity
- Experience using AI coding and tools such as GitHub Copilot
- Ability to design automated workflows for:
- Requirements analysis
- Specification generation
- User story creation
- Architecture and design decision records
- Task breakdown
- Test case generation
- Test plan creation
- Code generation
- Test execution
- Documentation generation
- Software Engineering
- Strong experience with .NET / C#
- Experience building APIs, services, backend systems, and cloud-native applications
- Good understanding of software architecture, clean code principles, design patterns, secure coding practices, and Test-Driven Development (TDD) methodologies.
- Experience with unit testing, integration testing, functional testing, and automated test execution
- Familiarity with test frameworks and automated testing tools used within the .NET ecosystem
3. What the Role Will Do
The AI Engineer will be responsible for designing and implementing an agentic SDLC harness capable of supporting the full software delivery lifecycle. Key responsibilities include:
- Design and build an AI Agentic Harness that orchestrates multiple AI agents across the SDLC
- Integrate the harness with development tools such as GitHub Copilot, GitHub, Azure DevOps, and CI/CD platforms
- Build agents that can generate Business and technical specifications
- Epics, features, and user stories
- Acceptance criteria
- Design decisions and architecture decision records
- Engineering tasks and implementation plans
- Test cases and test plans.
- .NET application code
- Infrastructure-as-Code templates
- CI/CD pipeline templates
- Deployment documentation
- Execute the harness to generate working .NET / C# code
- Build validation loops to review generated outputs for correctness, security, quality, and maintainability
- Create test automation capabilities that generate and execute tests against produced code
- Implement mechanisms for code review, quality checks, static analysis, and automated feedback
- Ensure generated applications are deployable into Azure environments
- Create reusable patterns, templates, prompts, workflows, and agent configurations
- Implement observability and traceability for agent decisions, tool usage, prompts, responses, and generated artifacts
- Work with architects, engineers, product owners, and platform teams to align the harness with enterprise engineering standards
- Contribute to security, compliance, and governance controls around AI-generated software delivery
- Continuously improve the harness based on output quality, developer feedback, and delivery outcomes
4. Nice to Have Skills
The following skills would be advantageous:
- Experience with Semantic Kernel, Azure AI Foundry, Azure OpenAI, or OpenAI APIs
- Experience with Model Context Protocol tools and agent tool integration
- Experience creating reusable software factory or platform engineering capabilities
- Familiarity with DevSecOps, secure SDLC, and automated security testing
- Experience building RAG-based systems or integrating AI agents with knowledge bases
- Knowledge of enterprise data privacy, responsible AI, and AI governance controls
- Experience working in Agile delivery environments
- Ability to create technical documentation, reference architectures, and engineering playbooks