Senior AI Engineer

About the role

iwconnect is hiring a Senior AI Engineer for its AI Solutions Delivery Team, which builds enterprise-grade AI applications such as RAG systems, agentic workflows and modern AI-powered solutions. The engineer owns the full development lifecycle, from architecture to deployment, leads projects with minimal oversight and guides other engineers when needed.

Key responsibilities

• Work directly with clients: turn business problems into AI solutions, explain how the technology works and its limits, and report progress clearly.
• Support proposals and pre-sales for new AI engagements.
• Lead AI engineers on engagements: set tasks, review work, give feedback and support growth and performance.
• Own delivery quality and the path from proof of concept to production.
• Design end-to-end AI-powered experiences and their underlying systems, including model selection, deployment patterns and infrastructure.
• Architect and build RAG pipelines: chunking (semantic, recursive, hierarchical), embeddings, retrieval, hybrid search, re-ranking and evaluation.
• Build agentic and multi-step workflows (LangChain, LangGraph or equivalent) with multi-agent designs and tool/API/MCP integration with enterprise systems.
• Deploy on a hyperscaler AI platform (Azure AI Foundry, AWS Bedrock, Google Vertex AI, Kubernetes-based or equivalent).
• Build for production: observability, evaluation, AI safety, bias and failure-mode handling, security and cost control.
• Write production code by hand and use AI development tools (GitHub Copilot, Cursor, Claude Code, etc.) in your work.

Required profile

• 5+ years in software/AI engineering with substantial hands-on delivery of production AI/LLM systems, not just PoCs or notebooks.
• Proven ability to take an AI solution from idea to production independently.
• Confident client-facing and team communication.
• Nice to have: experience with large regulated organisations (banks, insurers, government, utilities), formal team-leadership or performance-management experience, and relevant certifications.

Required skills

• Deep RAG expertise: chunking strategies, embedding models, vector databases, retrieval, re-ranking and evaluation.
• Agentic workflows and orchestration (LangChain, LangGraph or equivalent) and tool/API integration.
• Production-grade code in at least one of Python.NET / C#, Java or Node.js / TypeScript.
• Deployment of AI workloads on at least one hyperscaler AI platform.
• Knowledge graphs and graph-based retrieval (Neo4j, RDF/SPARQL, GraphRAG), NL2SQL, semantic layers and intelligent document processing.
• LLMOps / MLOps tooling and practices.