Gen AI Lead Developer

Requirement#2 - AI GitHub Copilot

•  
• Agentic SDLC Design — Architect and implement end-to-end AI-augmented SDLC pipelines using autonomous agents and sub-agents that handle tasks spanning requirements analysis, code generation, review, testing, and deployment.
• GitHub Copilot Agent Engineering — Design, configure, and extend GitHub Copilot agents, custom skills, and agent instructions to automate repetitive engineering tasks, enforce coding standards, and accelerate developer productivity across teams.
• Multi-Agent Orchestration — Build and manage multi-agent systems with clearly defined agent roles, skills, and handoff protocols — including planner agents, coder agents, reviewer agents, and test agents — ensuring reliable and deterministic outcomes.
• AI-Driven Code Quality & Governance — Integrate AI agents with static analysis, linting, and security scanning tools (e.g., SonarQube, CodeRabbit) to enforce quality gates, detect vulnerabilities, and provide real-time feedback within CI/CD pipelines.
• Automated Testing with AI Agents — Leverage AI agents to auto-generate unit tests, integration tests, BDD scenarios (Gherkin/Cucumber), and test data — continuously improving test coverage with minimal manual effort.
• Prompt Engineering & Skill Development — Design reusable, parameterised prompts and agent skills tailored to domain-specific engineering contexts (e.g., banking APIs, microservices, cloud-native patterns), enabling consistent and context-aware code generation.
• AI-Assisted Architecture & Design — Utilise AI agents in the design phase to generate architecture diagrams, ADRs (Architecture Decision Records), API contracts, and design documentation aligned with organisational standards.
• Engineering Best Practices & Standards — Define and enforce AI-assisted development standards including prompt governance, agent observability, output validation, hallucination mitigation, and human-in-the-loop checkpoints for critical workflows.
• Platform Engineering Integration — Embed agentic AI capabilities into internal developer platforms (IDPs), golden paths, and self-service toolchains — enabling teams to consume AI-powered workflows as reusable platform services.
• Continuous Learning & Innovation — Stay at the forefront of agentic AI frameworks (LangGraph, AutoGen, CrewAI, Copilot Extensions), evaluate emerging tools, run proof-of-concepts, and drive adoption of AI engineering innovations across the engineering community.

Skills & Experience:

• Hands-on experience with GitHub Copilot, Copilot Chat, and Copilot Extensions/Agents
• Proficiency in building multi-agent systems using frameworks such as LangGraph, AutoGen, or CrewAI
• Strong software engineering background across at least one major stack (Java/Spring, Python, Node.js)
• Familiarity with CI/CD pipelines, DevSecOps tooling, and quality engineering
• Experience with prompt engineering, RAG patterns, and LLM-based tooling
• Understanding of SDLC governance, testing standards, and code quality practices
   

Rrequirement#2 - AI AWS KIRO
Responsibilities:

• Spec-Driven Development with Kiro — Lead the adoption of AWS Kiro's spec-first approach, authoring structured requirements, design, and task specifications that drive autonomous, traceable code generation — ensuring every line of generated code is grounded in validated intent.
• Agent Hooks & Automation Design — Design and implement Kiro agent hooks (file-save triggers, event-driven automations) that autonomously enforce coding standards, run linting, regenerate documentation, and invoke downstream agents — reducing manual toil across the development lifecycle.
• Steering File Governance — Define and maintain Kiro steering files (.kiro/steering/) to encode organisational standards, architectural patterns, tech stack conventions, and security guardrails — ensuring every AI-assisted task aligns with enterprise engineering policies.
• Multi-Agent Workflow Orchestration — Architect multi-agent pipelines within Kiro where specialised sub-agents handle discrete SDLC concerns — requirements analysis, API contract generation, code scaffolding, test creation, and deployment validation — with clear handoffs and human-in-the-loop checkpoints.
• AI-Assisted Architecture & Design Artefacts — Utilise Kiro's agentic capabilities to auto-generate architecture decision records (ADRs), API specifications (OpenAPI), data models, and system design documents from high-level requirements — accelerating the design phase significantly.
• Automated Test Generation & Quality Engineering — Leverage Kiro agents to automatically generate unit tests, integration tests, BDD scenarios, and test data aligned to spec definitions — continuously improving coverage and shifting quality further left in the pipeline.
• CI/CD & DevSecOps Integration — Integrate Kiro agent workflows with CI/CD pipelines, connecting spec-driven outputs to automated build, security scanning (SAST/SCA), and deployment stages — creating a seamless, auditable path from spec to production.
• Prompt & Spec Engineering Excellence — Develop reusable, parameterised spec templates and prompt patterns tailored to domain-specific engineering contexts (microservices, cloud-native, event-driven architectures) — enabling consistent, high-quality AI outputs at scale.
• Engineering Best Practices & AI Governance — Establish standards for responsible agentic development including output validation, hallucination mitigation, spec versioning, agent observability, and change traceability — ensuring AI-generated artefacts meet the same rigour as human-authored code.
• Innovation, Enablement & Community — Stay at the forefront of AWS Kiro evolution and the broader agentic AI ecosystem (Amazon Q, Bedrock Agents, MCP integrations), run internal enablement sessions, publish reusable Kiro templates, and champion spec-driven agentic engineering across the organisation.

Skills & Experience:

• Hands-on experience with AWS Kiro
• Strong understanding of spec-driven development, requirements engineering, and SDLC governance
• Proficiency in AWS services (Bedrock, Lambda, CDK, ECS/EKS) and cloud-native architecture patterns
• Experience designing multi-agent systems with agent orchestration, tool use, and MCP integrations
• Solid software engineering background across at least one major stack (Java/Spring, Python, Node.js)
• Familiarity with CI/CD pipelines, DevSecOps tooling, and automated quality engineering
• Experience with prompt engineering, RAG patterns, and LLM-based development workflows