Required Skills & Experience
- 8+ years in software engineering or solution architecture, with at least 2 years focused on generative AI, LLMs or AI-assisted software development.
- Demonstrated hands-on experience with the AI-Driven Development Lifecycle (AI-DLC), including at least one implementation delivered for a team or organization.
- Hands-on experience with GitHub Spec Kit and spec-driven development, from writing specifications and plans through AI-generated tasks and implementation.
- Deep, practical expertise with GitHub Copilot (including agent mode and coding agents) and Microsoft Copilot tools.
- Strong GitHub skills: repositories, pull request workflows, branch strategy, GitHub Actions and CI/CD automation.
- Proven ability to apply AI to software testing, including test generation, test automation frameworks and test-driven or behavior-driven development.
- Experience designing architectures for enterprise applications on a major cloud platform (Azure preferred; AWS or GCP considered).
- A client-facing, forward deployed mindset: comfortable working directly with stakeholders, leading workshops and translating business goals into technical delivery.
- Experience with Microsoft Copilot Studio, Azure AI Foundry or Azure OpenAI, and building custom agents or MCP (Model Context Protocol) integrations.
- Familiarity with other agentic coding tools that support spec-driven workflows, such as Amazon Q Developer or Kiro.
- Background in domain-driven design and in modernizing legacy applications with AI assistance.
- Experience leading organizational change, developer enablement programs or AI Centers of Excellence.
- Relevant certifications, such as GitHub Copilot, Azure Solutions Architect Expert or Azure AI Engineer Associate.
- Highly regulated industry experience, preferred is banking
Nice to Have Skills & Experience
Job Description
A financial services client is planning to adopt and implement the AI-Driven Development Lifecycle (AI-DLC) across its real time payments software engineering organization and is looking for a hands-on AI Forward Deployed Engineer / AI Architect to lead the way. AI-DLC is an AI-native methodology in which AI acts as a central collaborator through every stage of delivery: it builds plans, asks clarifying questions and executes work, while people validate requirements and make the critical decisions. This person will be the client's practitioner and guide. They will design how AI-DLC fits the client's teams, stand up the tooling, and prove it on real projects, showing how AI can carry work all the way from business intent and requirements through design, code and automated testing. The ideal candidate has already used AI-DLC and GitHub Spec Kit in practice and can point to implementations they delivered, not just experiments. What you will do
- Lead the planning and rollout of AI-DLC, including its Inception, Construction and Operations phases, and adapt the methodology to the client's existing SDLC, teams and governance.
- Facilitate Mob Elaboration and Mob Construction sessions where product, engineering and QA teams validate AI-generated requirements, user stories, architecture and code in real time.
- Implement spec-driven development with GitHub Spec Kit, including project constitutions and the Specify, Plan, Tasks and Implement workflow, so every feature starts from a clear specification.
- Configure and integrate GitHub Copilot and the broader Microsoft Copilot ecosystem as the AI engines behind the workflow, including custom instructions, prompt files, agents and repository context.
- Build an end-to-end "AI all the way through" pipeline in which AI generates and maintains unit, integration and end-to-end tests, and testing is wired into CI/CD with GitHub Actions.
- Define the guardrails: human-in-the-loop approval points, code review standards, security and compliance checks, and quality gates for AI-generated work.
- Run pilot projects on both new (greenfield) and existing (brownfield) applications, measure results such as cycle time, quality and test coverage, and turn lessons learned into repeatable playbooks.
- Coach and upskill engineers, architects and leaders on AI-native ways of working, and serve as the trusted technical advisor to client stakeholders.