AI SDLC Lead Engineer

• 8+ years in software engineering, platform engineering, or technical architecture roles, with proven ownership of complex engineering workstreams. 
• Strong hands-on coding skills in Python plus at least one backend or systems language such as Go, Java, C, C++, or Rust. 
• Deep practical experience using AI coding agents and LLM-enabled SDLC workflows for large codebases, technical documentation, and engineering acceleration. 
• Good understanding of OpenStack-derived cloud software architectures, modular service decomposition, CI/CD, Kubernetes-based delivery, and platform operations. 
• Able to lead senior engineers in ambiguous environments, challenge AI outputs, and convert incomplete evidence into structured, actionable engineering decisions. 
• Comfortable working in high-accountability, confidentiality-sensitive enterprise programs where auditability, traceability, and sovereignty constraints are mandatory. 

Examples of market tools, models, and SDLC platforms expected 

• AI development environments such as Cursor, Windsurf, Claude Code, Continue, Cline, or VS Code-based extensions connected to enterprise-approved model endpoints. 
• Open-source, open-weight, or Chinese coding-capable models such as DeepSeek Coder, Qwen/Qwen-Coder, CodeGeeX, StarCoder, Code Llama, Mistral, or similar models operated through approved controls. 
• Agentic and SDLC workflow components such as LangGraph, OpenAI Agents SDK, AutoGen, LlamaIndex, RAG pipelines, evaluation loops, and structured tool-calling patterns. 
• Engineering environments including GitHub Enterprise, GitLab, Jenkins, ArgoCD, Helm, Docker, Kubernetes, private package registries, and terminal-native automation workflows. 

Key responsibilities 

• Define and lead AI-assisted SDLC patterns for repository intake, code exploration, service mapping, build diagnosis, documentation, and engineering evidence generation. 
• Guide analysis of OpenStack-derived control-plane services, APIs, dependencies, integration flows, and build structures across multiple repositories and teams. 
• Evaluate and operationalize AI development platforms, coding agents, and approved open-weight or Chinese coding model stacks for secure enterprise use cases. 
• Establish human-in-the-loop controls, quality gates, prompt libraries, reusable review patterns, and evidence standards for AI-generated engineering outputs. 
• Coach software engineers and platform specialists on safe, effective use of AI tools while coordinating with architecture, security, DevOps, and testing teams. 
• Produce senior stakeholder-ready artefacts including transition risks, service decomposition views, codebase maturity observations, and recommended engineering actions. 

• International, dynamic and collaborative environment.
• T-Social: social initiatives (sports, community, health,...).
• Hybrid work model (remote/on-site).
• Flexible working hours.