The Role Purpose:
We are seeking an AI Engineer to join our team, with a primary focus on designing, developing, and maintaining production-grade software solutions that leverage Large Language Models (LLMs), embedding models, and other generative technologies. This role emphasizes building scalable, reliable, and secure agentic solutions (including multi-agent systems) for external market-facing products and internal enterprise enablement.
The successful candidate will combine strong software engineering fundamentals with deep practical capability in retrieval-augmented generation (RAG), knowledge management, prompt/context engineering, model/tool orchestration, and AI governance guardrails.
The successful candidate will play a key role in building scalable systems for external market-facing products.
Your Responsibilities will include:
Design, develop, test, and deploy end-to-end GenAI-enabled software solutions (services, APIs, workflows, and product features).
Build agentic systems, including multi-agent architectures, tool-use patterns, orchestration flows, and production tooling integrations.
Design and implement RAG pipelines for both product and enterprise contexts, including knowledge-based curation, ingestion, document processing, chunking strategies, embedding generation, retrieval tuning, and answer grounding.
Develop and operationalize robust prompt and context engineering practices (prompt templating, context window management, instruction hierarchy, tool routing, and response formatting).
Implement agent memory management patterns and frameworks to support short-term and long-term memory, personalization, and session continuity (where applicable).
Integrate and operate model providers and runtimes for production use-cases, including hosted APIs and self-hosted inference, optimizing for latency, cost, throughput, and reliability.
Develop microservices and APIs that expose GenAI/agent capabilities to web applications and downstream systems; maintain strong engineering standards for versioning, observability, and backward compatibility.
Design and maintain data stores supporting GenAI applications, including relational, vector, and graph patterns to enable retrieval, reasoning, and relationship-aware experiences.
Implement AI Governance practices: apply and monitor guardrails (policy enforcement, content filtering, PII handling, prompt injection defences, auditability, and safe tool execution).
Evaluation and monitoring approaches for GenAI systems (quality, grounding, safety, latency, cost), contributing to continuous improvement initiatives.
Collaborate with cross-functional teams (Product, Engineering, UX, Data/ML, Security, Compliance) to translate business requirements into technically sound solutions.
Participate in code reviews, architectural discussions, and agile planning sessions; contribute to internal standards, patterns, and reusable components.
Maintain and enhance legacy systems where required, integrating GenAI functionality safely without compromising stability.
The ideal candidate for the role will have the following qualifications, experience and knowledge:
Educational Background:
Bachelor’s degree in computer science, Information Technology, Data Science, Artificial Intelligence, Software Engineering, or equivalent
Postgraduate qualification in Artificial Intelligence, Machine Learning, Data Science, or Applied Mathematics is advantageous
Relevant certifications are advantageous (examples include Microsoft Azure AI Engineer, AWS Machine Learning, or similar cloud/AI certifications).
Work Experience:
1-3 years of experience in delivering production-grade software (greenfield and brownfield), including backend services and customer-facing modules.
Proven hands-on experience building and deploying GenAI solutions in production, including LLM-powered features, RAG-based systems, or agentic workflows.
Experience implementing governance controls and operational monitoring for GenAI systems in real-world environments.
Strong practical exposure to modern software engineering practices: CI/CD, testing, code review, observability, and secure API design.
Knowledge:
Strong understanding of LLM/embedding fundamentals as applied in production systems (retrieval, grounding, context shaping, evaluation, and failure modes).
Knowledge of multi-agent patterns, tool/function calling (MCP), workflow orchestration, and safe execution boundaries.
Understanding of data management strategies for GenAI (document pipelines, vector search, graph relationships, and relational integrity).
Familiarity with data privacy principles, security-by-design, and governance expectations relevant to enterprise-grade AI solutions.
Technical Skills:
Core Engineering & Platforms
Python (GenAI services, orchestration, data pipelines), C#, REST APIs, microservices, event-driven systems (Kafka).
Strong engineering fundamentals (clean architecture, testing, security, performance).
GenAI, Agents & RAG
Prompt and context engineering, agent frameworks (e.g. LangChain, LangGraph, LangSmith, CrewAI, Semantic Kernel), workflow automation (e.g. n8n).
Experience with hosted and self-hosted models (OpenAI/Azure/AWS, Ollama, vLLM). RAG systems: document ingestion, embeddings, hybrid retrieval, reranking, citations, and knowledge lifecycle management.
Data, Memory & Storage
PostgreSQL (incl. timescale), vector DBs (Qdrant, Milvus), graph DBs (Neo4j, Apache AGE).
Agent memory patterns (session, long-term, summarization) with privacy and risk controls.
Security, Governance & Ops
GenAI guardrails (prompt/tool injection defence, PII handling, auditing).
Cloud & DevOps (Azure/AWS, CI/CD, Git, Docker/Kubernetes). Observability for LLM systems. Agile delivery and GenAI-specific testing/evaluation