AI Engineer

Stack

Responsibilities

• ▹Design, develop, test, and deploy end-to-end GenAI-enabled software solutions
• ▹Build agentic systems, including multi-agent architectures and tool-use patterns
• ▹Design and implement RAG pipelines (document processing, chunking, embedding, retrieval tuning)
• ▹Develop robust prompt and context engineering practices
• ▹Implement agent memory management patterns (short- and long-term memory, personalization)
• ▹Integrate and operate model providers and runtimes (hosted APIs, self-hosted inference)
• ▹Develop microservices and APIs exposing GenAI/agent capabilities
• ▹Design and maintain data stores for GenAI applications (relational, vector, graph)
• ▹Implement AI Governance practices: guardrails, content filtering, PII handling, prompt injection defences
• ▹Develop evaluation and monitoring approaches for GenAI systems
• ▹Collaborate with cross-functional teams (Product, Engineering, UX, Data/ML, Security, Compliance)
• ▹Participate in code reviews and architectural discussions
• ▹Maintain and enhance legacy systems with GenAI functionality

Requirements

• ▹Bachelor's degree in Computer Science, Information Technology, Data Science, AI, or Software Engineering
• ▹3-4 years of experience delivering production-grade software
• ▹Proven hands-on experience building and deploying GenAI solutions (LLM-powered features, RAG systems, agentic workflows) in production
• ▹Experience implementing governance controls and operational monitoring for GenAI systems
• ▹Strong practical exposure to CI/CD, testing, code review, observability, and secure API design
• ▹Strong understanding of LLM/embedding fundamentals (retrieval, grounding, context shaping, evaluation)
• ▹Knowledge of multi-agent patterns, tool/function calling (MCP), workflow orchestration
• ▹Python (GenAI services, orchestration, data pipelines)
• ▹C#, REST APIs, microservices, event-driven systems (Kafka)
• ▹Strong engineering fundamentals (clean architecture, testing, security, performance)

Nice to have

• ▹Postgraduate qualification in AI, Machine Learning, Data Science, or Applied Mathematics
• ▹Relevant certifications (e.g. Microsoft Azure AI Engineer, AWS Machine Learning)
• ▹Familiarity with data privacy principles and security-by-design for enterprise AI

Soft skills