Agentic AI Engineer

The role requires adaptability, breadth of thinking, and the discipline to bring rigorous engineering to every deliverable. The Agentic AI Engineer is personally accountable for the quality and reliability of every deliverable produced, on both internal and client engagements. The work spans agent-based systems, web applications, data engineering, and infrastructure, with agentic pair programming as the primary working mode.

Engineering discipline, sound technical judgment, and adherence to the team's quality standards are expected on every piece of work. The ideal candidate is currently working with agentic AI systems in a hands-on capacity and has a track record of shipping production systems. Professional experience extends beyond generative AI alone, with a broader engineering foundation that demonstrates range across problem types.

The role calls for an engineer who delivers consistently, owns what they ship, and brings the same rigor to unfamiliar problems as to familiar ones .\n\nREQUIRED QUALIFICATIONS:\nEngineering Experience:\nProfessional engineering experience that extends beyond generative AI, demonstrating a broader technical foundation.\nCurrently or recently working with agentic AI systems in a hands-on capacity.\nExperience building POCs, demos, or production systems using agentic methods.\n\nTechnical Requirements:\nPython as primary language.\nMicrosoft Azure required as the primary cloud platform.\nHands-on experience building with Azure AI Foundry.\nClaude Code experience and expertise required, including hands-on development of skills and plugins on the platform. This is non-negotiable for the role.\nLangGraph experience required. Demonstrated ability to design state graphs, conditional edges, and multi-agent compositions.\nModel Context Protocol experience required.

Comfortable designing tool calls and building protocol wrappers.\nAgentic pair programming with generative AI as the primary working mode. Prior experience is required.\nPydantic for data validation and structured outputs across agent systems and APIs.\nSQL proficiency and PostgreSQL experience.\nVector database experience (pgvector, Azure AI Search, or similar).\nFamiliarity with modern data platforms such as Snowflake and Databricks.\nMulti-step agent systems with proper evaluation and validation.\nStrong fluency across modern frontier language models such as the GPT, Claude, and Gemini model families. Model selection is driven by the requirements of each task and the practical considerations of cost.\nThe discipline to choose mature, proven frameworks for AI engineering work.

Technical decisions are grounded in clear engineering justification and supported by data.\nDocker and containerization for development and deployment workflows.\nFastAPI or equivalent web frameworks for building APIs and backend services.\nWorking knowledge of GitHub workflows, code review discipline, and infrastructure-as-code patterns.\n\nPreferred Qualifications:\nAlthough Microsoft Azure is the primary platform, Google Cloud Platform experience is also valuable and applicable to the practice's work.\nFamiliarity with Azure Container Apps, Azure Kubernetes Services, or similar container orchestration platforms.\nFamiliarity with Apache Software Foundation tools such as Apache Airflow, Apache Kafka, and Apache Flink.\nExperience with LangChain, PyTorch, or other AI and machine learning frameworks.\nCrewAI or other multi-agent frameworks.\nLlamaIndex for RAG and data ingestion workflows.\nCelery and Redis for background task processing and caching.\nFamiliarity with A2A (Agent-to-Agent) protocol for inter-agent communication.\nExperience with modern natural language processing tools, including embedding models and entity recognition.\nFamiliarity with vision-language model integration for multi-modal AI use cases.\nExperience working in regulated markets, including the compliance and risk-management disciplines such environments require.\nPlaywright for end-to-end testing automation.\nFamiliarity with hybrid architectures that integrate deterministic and generative AI techniques.