Agentic AI Engineer

Demonstrated range across engineering disciplines, comfortable moving between generative AI development, web development, database work, and infrastructure as the practice's engagements shift.

Agentic AI Development (45%)

• Build AI systems for internal and client engagements, from initial POC through production delivery.
• Design and implement agent-based solutions for complex, multi-step problems across the practice's diverse engagement portfolio.
• Build POCs and demos that demonstrate technical feasibility and value to stakeholders.
• Evaluate and select the right approach for each problem, including knowing when an agent-based approach is appropriate and when a simpler method fits.
• Participate in system design within the team, contributing architectural thinking and implementation expertise.
• Own the full lifecycle of systems: design, implementation, evaluation, and reliability.

Engineering and Development (25%)

• Build and maintain web applications, APIs, and backend services for internal and client engagements.
• Design and work with database schemas, write and optimize queries, and manage data across relational and vector database systems.
• Build data pipelines and integrations across the practice's data platforms.
• Contribute to infrastructure work, including containerized deployments and cloud configuration.
• Move between technical areas with engineering discipline, applying the same rigor regardless of the specific technology or context.
• Deliver work that meets the team's standards across both internal initiatives and solutions developed for the practice's client portfolio.

Quality and Delivery Excellence (20%)

• Write and maintain tests (unit, integration, end-to-end) as part of every deliverable.
• Participate in code reviews with substantive technical feedback, both giving and receiving.
• Maintain documentation for systems built, including architecture decisions, setup instructions, and integration points.
• Apply evaluation discipline to agent systems, including structured evaluation harnesses and observability for deployed systems.
• Meet delivery commitments on time and communicate accurately on progress and blockers.
• Uphold the team's code quality standards, testing practices, and documentation requirements across all work.

Growth and Collaboration (10%)

• Stay current with developments in the agentic AI landscape, language-model orchestration, and the broader AI engineering field.
• Learn new tools, frameworks, and patterns as the practice adopts them, working from reference implementations and team guidance.
• Actively expand technical skills and depth across the practice's engineering domains, pursuing breadth as the engagement portfolio evolves.
• Contribute to team knowledge by sharing findings from new tools, techniques, and engagement experiences.
• Incorporate feedback from code reviews, system evaluations, and team retrospectives into ongoing work.
• Collaborate effectively within the distributed team, including responsive communication and proactive escalation of blockers.

Technical Requirements

• Python as primary language.
• Hands-on experience building with Azure AI Foundry.
• LangGraph experience - Demonstrated ability to design state graphs, conditional edges, and multi-agent compositions.
• Model Context Protocol experience - Comfortable designing tool calls and building protocol wrappers.
• Agentic pair programming with generative AI as the primary working mode. Prior experience is required.
• Pydantic for data validation and structured outputs across agent systems and APIs.
• SQL proficiency and PostgreSQL experience.
• Vector database experience (pgvector, Azure AI Search, or similar).
• Familiarity with modern data platforms such as Snowflake and Databricks.
• Multi-step agent systems with proper evaluation and validation.
• Strong fluency across modern frontier language models such as the GPT, Claude, and Gemini model families.
• Docker and containerization for development and deployment workflows.
• FastAPI or equivalent web frameworks for building APIs and backend services.
• Working knowledge of GitHub workflows, code review discipline, and infrastructure-as-code patterns.