***We are unable to sponsor as this is a permanent full-time role***
***Hybrid, 3 days onsite, 2 days remote***
Responsibilities:
· Own the design and delivery of agentic AI systems end-to-end, from architecture through production deployment
· Architect agent orchestration patterns, tool and context integration, and evaluation pipelines for reliability in a regulated environment
· Own AI infrastructure supporting AIRE's agents and applications on AWS, and contribute to the team's growing infrastructure self-sufficiency
· Implement technical safeguards against AI-specific risks, including hallucination detection, prompt injection defense, and output validation, in collaboration with company AI Governance function
· Build audit logging and human-in-the-loop checkpoints into agentic workflows so agent actions remain traceable and reviewable in a regulated environment
Qualifications:
· Bachelor's degree in Computer Science, Engineering, or a related technical field; Master's preferred
· 4-7 years of software engineering experience, with production AI/LLM systems experience preferred
· Strong Python; proficient SQL; solid distributed systems and API design fundamentals
· Hands-on experience building LLM-powered applications or agentic systems
· Working knowledge of AI-specific risk areas (prompt injection, output validation, hallucination mitigation, data privacy), or demonstrated ability to build this expertise quickly
· Cloud infrastructure experience (AWS preferred); comfort with Docker, CI/CD, and containerization fundamentals
· Direct experience with Claude, the Anthropic API, or Claude.ai/Console
· Experience designing agent orchestration or Model Context Protocol (MCP)-based integrations
· Production experience operating LLM-powered applications or agentic systems at scale
