- Commercial Experience & Technical Leadership: 5+ years in commercial software development, including 2+ years coordinating engineering practices/teams, and 3+ years focused on Node.js & TypeScript backend development.
- Core Technology Stack: Strong backend proficiency in Node.js / TypeScript, working knowledge of Vue 3, hands‑on experience with MySQL, MongoDB, Redis, and message queues (RabbitMQ or Bull).
- Agentic AI & Spec-Driven Engineering: 1+ year of daily experience applying agentic workflows on production projects (e.g., Claude Code, plan modes, sub-agents, multi-session git worktrees, MCP servers) while maintaining active hands‑on coding.
- Process & Context Design: Practical experience with Spec-Driven Development frameworks and setting up standardised agent environments (e.g., repository rules, custom capabilities, execution permissions, context architecture).
- Practice Adoption & Governance: Track record of defining and embedding technical standards across engineering streams, with an understanding of AI security risks (secret isolation, personal data protection, code verification).
- Stakeholder Management: Experience running technical discovery sessions, presenting architecture/process changes, and working closely with senior decision-makers.
Role Scope & Requirements
- Commercial Experience & Technical Leadership: 5+ years in commercial software development, including 2+ years coordinating engineering practices/teams, and 3+ years focused on Node.js & TypeScript backend development.
- Core Technology Stack: Strong backend proficiency in Node.js / TypeScript, working knowledge of Vue 3, hands‑on experience with MySQL, MongoDB, Redis, and message queues (RabbitMQ or Bull).
- Agentic AI & Spec-Driven Engineering: 1+ year of daily experience applying agentic workflows on production projects (e.g., Claude Code, plan modes, sub-agents, multi-session git worktrees, MCP servers) while maintaining active hands‑on coding.
- Process & Context Design: Practical experience with Spec-Driven Development frameworks and setting up standardised agent environments (e.g., repository rules, custom capabilities, execution permissions, context architecture).
- Practice Adoption & Governance: Track record of defining and embedding technical standards across engineering streams, with an understanding of AI security risks (secret isolation, personal data protection, code verification).
- Stakeholder Management: Experience running technical discovery sessions, presenting architecture/process changes, and working closely with senior decision-makers.
Nice-to-Have Experience:
- Professional background in technical consulting, forward-deployed engineering, or solutions architecture.
- Secondary technology exposure: PHP / legacy frameworks, NestJS, Fastify, PostgreSQL, or analytical databases (e.g., ClickHouse).
- Experience with spec-driven legacy system migrations and automated data parity testing.
- Automated AI-assisted code review pipelines in CI/CD (GitLab CI preferred) and DORA metric tracking.
- Domain exposure: High-load platforms, FinTech, or payment provider integrations.
Key Responsibilities
- AI SDLC Architecture & Rollout: Design and implement an end-to-end AI-native delivery process covering specification, automated agent execution, code reviews, and verification.
- Pilot Leadership & Hands-on Delivery: Lead pilot implementation streams hands‑on while providing technical direction to engineers participating in the rollout.
- Discovery & Scope Alignment: Collaborate with key project stakeholders to identify pilot scopes, establish success benchmarks, and map execution roadmaps.
- Context & Security Governance: Establish standardised AI repository context structures, define usage guidelines, and enforce security policies (secret isolation, permission boundaries, code attribution).
- Quality Assurance Strategy: Implement validation patterns for agent outputs, including critical-path characterisation tests, automated linting, and CI-integrated review checks.
- Knowledge Sharing & Mentoring: Conduct technical workshops, mentor engineers on agentic workflows, and report delivery metrics (cycle times, adoption rates, quality benchmarks) to technical management.
Project Overview
The project focuses on modernising software delivery practices for a live, high-load platform. The initiative aims to introduce an AI-native development lifecycle (AI SDLC) driving end-to-end delivery using AI agents, spec-driven engineering practices, and standardised governance. This consultancy role leads the design, execution, and team-wide adoption of these practices embedded alongside the core project stream.