AI Development Engineer

We are looking for an AI Development Engineer who is passionate about solving complex engineering problems and using AI to improve the speed, quality, and cost efficiency of software development.

The role involves rethinking the traditional approach to software engineering — moving from coding and implementation-heavy workflows to solution orchestration, structured thinking, detailed specifications, system design, and validation.

You will work on building intelligent, agentic applications that combine AI capabilities with traditional engineering systems. The focus is on using AI effectively while ensuring that the solutions we build remain reliable, secure, scalable, maintainable, and production-ready.

Key Responsibilities

Requirement Clarity and Engineering Design

• Develop a deep understanding of technical requirements and system-level design to minimise rework and reduce the risk of AI-generated errors.
• Translate ambiguous product and business ideas into clear, structured technical specifications.
• Create specifications that serve as a reliable source of truth for both engineering teams and AI systems.

Engineering Excellence

• Establish practices to minimise functional defects and operational issues caused by AI-generated code.
• Identify and eliminate code bloat, redundant logic, dead code, and unnecessary complexity.
• Ensure AI-generated code remains understandable, maintainable, and easy for engineers to navigate.
• Build the right documentation and engineering artefacts so that AI-generated code does not become a black box.
• Incorporate security best practices into prompts, context, and code-generation workflows.

Agentic Applications

• Build, maintain, and scale production systems that leverage Generative AI to transform user experiences.
• Design and monitor agentic workflows where AI components interact with traditional microservices to solve complex business problems.
• Explore and implement ways to move from manual workflows to intelligent, agent-driven applications.

Operational Excellence

• Focus on rigorous validation as AI accelerates development and output.
• Ensure automated outputs meet high standards of security, performance, reliability, and intended functionality.
• Build deep observability into services and systems to identify and address production issues.
• Explore self-healing production workflows where AI can interpret logs, identify issues, and suggest real-time fixes.

Cost Efficiency

• Optimise inference costs through effective prompt engineering, model selection, tool usage, and workflow design.
• Balance model performance, token consumption, and overall business ROI.
• Identify and reduce technical debt caused by AI-generated code and redundant implementations before they affect system performance or cloud costs.

Organisational Leadership and Collaboration

• Work closely with Product, Production Engineering, Security, and other stakeholders to align AI capabilities with business goals and responsible AI practices.
• Encourage a culture where engineers can experiment with new AI workflows, learn from failures, and continuously improve.
• Mentor junior engineers and help drive the shift from traditional coding practices towards AI-assisted engineering and system orchestration.