Senior AI Engineer (United Kingdom)

Location: Remote, United Kingdom

Company

hirify.global provides a software platform used across quality manufacturing, life sciences, public health, forensics, and environmental sciences.

What you will do

• Design and build the agent runtime, including planning and execution loops, tool calling, state management, durable execution, failure recovery, coordination, and handoffs.
• Build production agents for domain workflows, grounding decisions in authoritative enterprise data and supporting human approval, overrides, uncertainty handling, and evidence capture.
• Develop evaluation harnesses and production metrics for task completion, tool-call correctness, groundedness, trajectory quality, reliability, latency, cost, and human intervention.
• Implement guardrails, fallbacks, timeouts, cost ceilings, tracing, and safeguards against prompt injection, unsafe tool use, excessive permissions, and data leakage.
• Integrate agents with platform APIs and third-party enterprise systems, including retrieval and permission-aware context pipelines with complete audit trails.
• Build and operate backend services and infrastructure on AWS, contribute to architecture decisions, infrastructure-as-code, and deployment pipelines.

Requirements

• 6+ years of software engineering experience with production systems.
• Production experience with LLM systems, including tool-using or multi-step agentic workflows beyond basic prompting and chat interfaces.
• Strong understanding of LLM behavior, limitations, failure modes, and error compounding across multi-step runs.
• Experience with LLM APIs, tool and function calling, planning and execution loops, and evaluation of non-deterministic systems.
• Solid backend and cloud experience with AWS or an equivalent platform.
• Proficiency in TypeScript and/or Python, plus the ability to own production systems end-to-end.

Nice to have

• C# and Microsoft .NET Framework experience.
• MCP and other tool or interoperability protocols.
• Agent-specific evaluation pipelines, retrieval and grounding techniques, or regulated-system experience involving validation and audit trails.
• Workflow and durable-execution platforms such as Temporal, Step Functions, or n8n.
• Containerization, orchestration, and infrastructure-as-code experience with Kubernetes, ECS, EKS, Terraform, or similar tools.

Culture & Benefits

• Work on AI systems where accuracy, traceability, validation, and controllability are essential.
• Balance accuracy, latency, reliability, and cost when designing production systems.
• Choose conventional software over AI when it is the more appropriate solution.
• Contribute to ambiguous, technically complex architecture problems and own systems across their full lifecycle.