AI Engineer

Role Summary

We are looking for an AI Engineer to design, develop, and deploy reliable AI-powered applications and intelligent workflows. The role focuses on building LLM and generative AI solutions, including retrieval-augmented generation, agent workflows, AI integrations, and supporting data pipelines.

You will work closely with business users, product, engineering, and data teams to translate requirements into practical AI solutions, evaluate and improve system performance, and support applications through deployment and ongoing maintenance.

Job Responsibilities:

Build AI applications

• Develop Python services, APIs, and workflows using model APIs, structured outputs, and tool calling.
• Integrate AI applications with databases and business systems.
• Work with users to understand requirements and continuously improve solutions based on feedback.

Engineer useful context

• Implement document ingestion, chunking, embeddings, retrieval, and context assembly.
• Improve source relevance, freshness, and citations while managing instructions, conversation history, and token budgets.
• Apply appropriate data-access and security rules when retrieving information.

Develop agent workflows and harnesses

• Implement tool schemas, execution steps, state handling, retries, timeouts, and logging using established patterns.
• Add validation and human-approval steps where required.
• Test workflow reliability and recovery from failed tool calls.

Evaluate and debug

• Create representative test datasets and automated checks.
• Analyse traces to diagnose retrieval, model, and tool-related issues.
• Evaluate changes based on task success, answer quality, latency, and cost.
• Document system limitations, issues, and regressions.

Build the data foundations

• Write SQL and data-processing code to ingest, clean, and transform structured and unstructured data.
• Validate schemas, missing values, duplicates, and data freshness.
• Help maintain reliable data pipelines, indexes, and retrieval systems.

Use AI coding tools responsibly

• Use coding assistants and AI agents to accelerate implementation and debugging.
• Maintain clear repository instructions and task context.
• Review AI-generated code, run meaningful tests, and understand and explain the resulting implementation.

Ship and support software

• Contribute tested code through Git and code review.
• Support the packaging, deployment, monitoring, and maintenance of AI applications.
• Investigate defects and maintain technical documentation.
• Follow access-control, secrets-management, security, and data-protection standards.

Job Requirements:

• University degree or equivalent in Computer Science, Artificial Intelligence, Data Science, Engineering, Mathematics or a related discipline.
• At least 2 years of relevant experience in AI engineering, software engineering, data engineering, machine learning, or a related technical role.
• Strong proficiency in Python and SQL, with experience in APIs/JSON, Git, debugging, and automated testing.
• Hands-on experience building and deploying AI/LLM applications, including at least one practical project integrating retrieval, databases, APIs, or tools.
• Good understanding of LLM fundamentals, including tokens, context windows, embeddings, RAG, structured outputs, and tool calling.
• Understanding of data and ML fundamentals, including data preparation, training vs. inference, validation, overfitting, data leakage, neural networks, and transformers.
• Experience translating business requirements into practical technical solutions and working with users/stakeholders.
• Strong problem-solving and engineering mindset, with the ability to troubleshoot, test solutions, explain technical decisions, and adapt quickly to new technologies and tools.
• Familiarity with AI/agent frameworks, vector databases, cloud platforms, or MLOps is an advantage.