Agentic Artificial Intelligence Engineer

Role Summary

We are looking for an Agentic AI Engineer to design, build and deploy autonomous AI systems that execute real operational workflows across the business.

This is a hands-on engineering role, not a research or advisory position. You will own the agent stack end to end — from architecture and tool integration through to evaluation, monitoring and production reliability. Success is measured by systems that run daily without supervision, not by prototypes or proofs of concept.

Key Responsibilities

Design & Development

• Architect and build multi-agent systems using LangGraph, LangChain or equivalent orchestration frameworks

• Implement LLM tool-calling, planning loops, state management and multi-step task execution

• Develop and maintain MCP servers and custom tool integrations

• Build retrieval pipelines (RAG) using vector stores and structured data sources

Integration

• Connect agents to enterprise systems — ERP, databases, internal APIs and third-party services

• Work with business stakeholders to translate manual processes into automated agentic workflows

• Ensure secure handling of company data within all AI systems

Production & Reliability

• Implement evaluation frameworks, regression testing and quality benchmarks for agent behaviour

• Build observability: tracing, logging, error handling, retry logic and fallback paths

• Monitor and optimise latency, token consumption and operating cost at scale

• Define and enforce guardrails, access controls and human-in-the-loop checkpoints

Ownership

• Take initiatives from concept to production deployment and ongoing support

• Document architecture, decisions and operating procedures

• Stay current with the agentic AI ecosystem and recommend adoption where it delivers measurable value

Required Qualifications

• Bachelor’s degree in Computer Science, Software Engineering or a related field

• 3+ years of professional software engineering experience with expert-level Python

• 1–2 years of hands-on experience building agentic AI systems — multi-agent architectures, tool-calling and autonomous workflows deployed in a production or live business environment

• Demonstrable experience with LLM APIs (Anthropic, OpenAI, Azure OpenAI or equivalent)

• Strong working knowledge of RAG, embeddings, vector databases and context management

• Experience with REST APIs, relational databases and system integration

• Proficiency with Git, CI/CD pipelines and containerised deployment (Docker)

• Practical understanding of prompt engineering, agent evaluation and failure-mode debugging

• Strong written and verbal communication in English