AI Engineer; Agentic Systems

The Role

We’re looking for an AI Engineer to help build and run customer‑facing AI agent capabilities in production. You’ll work in a team of highly skilled engineers delivering reliable, secure, and observable agent‑driven workflows. Our orchestration backbone is Akka (Java), deployed on AWS, with top observability/evaluation platform and Postgres + pgvector for retrieval.

This is an engineering‑first role: you’ll focus on distributed systems, orchestration, robustness, and production operations—bringing AI agent components into a dependable runtime.

• Build and operate customer‑facing services that incorporate AI agents and tool‑using workflows
• Integrate retrieval components using Postgres + pgvector (query patterns, latency considerations, embedding/retrieval flows)
• Instrument, monitor, and improve agent quality using observability tools (quality signals, evaluation/regression tracking, incident triage)
• Engineer for reliability and safety: timeouts, retries, idempotency, graceful degradation, auditability, and secure service integration
• Collaborate with product/engineering stakeholders to translate requirements into robust designs, delivery plans, and runbooks

• Eligible and willing to pass relevant background checks
• PhD or Master’s degree in Computer Science / AI / Data Science / Machine Learning / Engineering (or equivalent practical experience)
• At least 3+ years post‑graduate experience delivering production software systems and building and operating scalable backend/distributed systems (high‑concurrency services, reliability patterns, production operations)
• Strong Java engineering skills and experience with concurrent/distributed systems
• Experience building customer‑facing services with high reliability expectations (timeouts, retries, observability, performance)
• Familiarity with AWS fundamentals for deploying and operating services (including security/IAM awareness)
• Strong engineering practices: testing, code review, CI/CD, documentation, and operational readiness

• Hands‑on experience with Akka in production (actors/streams; reliability patterns such as supervision)
• Python experience (useful for integrating AI/agent tooling and adjacent components)
• Experience with LLM/agentic systems (tool calling, structured outputs, evaluation practices)
• Experience with Arize (or similar ML/LLM observability tooling)
• Experience with Postgres + pgvector and retrieval optimisation
• Security‑by‑design experience for AI systems (PII handling, prompt injection mitigation, least privilege, audit trails)

• Work on a state‑of‑the‑art high‑profile, production AI system with modern runtime and observability practices
• A collaborative Northern Ireland‑based engineering team with hybrid flexibility
• Competitive package and professional growth opportunities