AI Engineer / Agent Developer

Role overview

Agent development and engineering

• Build, configure, and test AI agents for defined business use cases.
• Apply prompt engineering, RAG, workflow automation, API development, and tool integration.
• Implement reasoning patterns, tool selection, memory, context management, structured outputs, and guardrails.
• Use version control, code review, environment separation, automated testing, and CI/CD.

Prototyping and production deployment

• Develop rapid prototypes with clear assumptions and limitations.
• Transition validated prototypes into production through hardening, performance tuning, and operational documentation.
• Prepare release artefacts, runbooks, and support handover materials.
• Contribute reusable libraries, components, prompt templates, and evaluation harnesses.

Enterprise systems integration

• Connect agents with ERP, CRM, HRMS, procurement, document repositories, databases, and workflow tools.
• Build and consume secure APIs with authentication, rate limits, error handling, and retry logic.
• Implement human-in-the-loop approvals and escalation routes.
• Coordinate data contracts, sandbox access, regression testing, and release windows with application owners.

Monitoring and quality assurance

• Monitor accuracy, reliability, latency, and exception handling in test and production environments.
• Build evaluation datasets and automated test suites to detect regressions.
• Investigate failures to root cause and implement corrective changes with documented evidence.
• Track token consumption and inference cost and optimize model selection, context size, and caching.

Security and collaboration

• Work with AI leads, data engineers, application specialists, and business users throughout delivery.
• Apply data classification, secrets management, cybersecurity, data protection, and least-privilege access requirements.
• Maintain documentation covering architecture, prompts, integrations, limitations, and support procedures.
• Demonstrate capabilities, gather structured feedback, and improve real-world usage.

Requirements

• Ability to build, configure, and test AI agents for defined business use cases.
• Hands-on capability in prompt engineering, RAG, workflow automation, API development, and tool integration.
• Ability to implement reasoning patterns, tool selection, memory and context management, and structured outputs.
• Ability to design guardrails including input validation, output constraints, confidence thresholds, and safe failure behaviour.
• Working knowledge of version control, code review, environment separation, automated testing, and CI/CD pipelines.
• Ability to connect agents securely with enterprise systems, documents, databases, and workflow tools.
• Ability to build and consume secure APIs with authentication, rate limits, error handling, and retry logic.
• Ability to implement human-in-the-loop approvals and escalation routes.
• Ability to monitor agent accuracy, reliability, latency, cost, and exception handling.
• Ability to investigate failures, identify root causes, and implement evidence-based corrective changes.
• Ability to apply cybersecurity and data protection requirements, including data classification and least-privilege access.
• Ability to document architecture, prompts, integrations, limitations, and support procedures.