Software Engineer - AI Products Agent Prototype/Building (AI)

Location: Remote, UK

Company

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

What you will do

• Design and build agent runtimes covering planning and execution loops, tool calling, state management, durable execution, failure recovery, coordination, and handoffs.
• Build production agents from domain workflows, grounding decisions in authoritative enterprise data and incorporating human approval gates, overrides, uncertainty handling, and decision evidence.
• 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, observability, tracing, and safeguards against prompt injection, unsafe tool use, excessive permissions, and data leakage.
• Integrate agents with platform APIs and third-party enterprise systems, creating permission-aware retrieval and context pipelines with complete audit trails.
• Build and operate backend services and deployment infrastructure on AWS, including Lambda, API Gateway, DynamoDB, Step Functions, Terraform, and related services.

Requirements

• 6+ years of software engineering experience, including production systems.
• Experience building production LLM systems with tool-using or multi-step agentic workflows beyond simple 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, with 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 and metrics, retrieval and grounding techniques, or regulated and domain-heavy systems.
• Workflow and durable-execution platforms such as Temporal, Step Functions, or n8n.
• Containerization, orchestration, and infrastructure as code with ECS, EKS, Kubernetes, Terraform, or similar tools.

Culture & Benefits

• Full-time remote work for the UK-based role.
• Work on systems requiring strict accuracy, traceability, validation, and controlled change.
• Opportunity to own significant parts of the architecture and contribute to key technical decisions.
• Equal opportunity employment.