AI Engineer

Key Responsibilities

• AI Feature Design Delivery - Design, build and run AI powered features using large language models, translating product ideas into reliable, scalable production systems that deliver measurable impact.
• LLM Integration System Architecture - Integrate LLMs into existing applications and services, shaping backend architectures and APIs that balance performance, cost, security and maintainability.
• Prompt Engineering Model Optimisation - Develop, test and refine prompt strategies to improve model accuracy, safety, latency and cost efficiency across different use cases.
• Hands-On Engineering - Build and maintain backend services and APIs using TypeScript and modern frameworks, contributing clean, well documented and maintainable code aligned with engineering best practice.
• Cross-Functional Collaboration - Work closely with product, data and design partners to identify high value AI opportunities and shape solutions that are feasible, testable and aligned to user needs.
• Evaluation Monitoring - Define and implement evaluation approaches for LLM based systems, including logging, metrics and experimentation, to continuously improve quality and reliability in production.
• Scalable AI Patterns - Contribute to shared approaches, architectural patterns and standards for building AI driven features across the platform.
• Risk, Privacy Cost Awareness - Make informed engineering decisions that consider data privacy, model risk, operational resilience and commercial constraints.
• Continuous Learning Innovation - Stay current with emerging AI technologies, tools and techniques, proactively recommending improvements that enhance outcomes for users and teams.

Knowledge, skills and experience required

• A strong foundation in software engineering, with hands-on experience building, shipping and operating scalable, production-grade systems.
• Proven experience working with modern JavaScript and TypeScript stacks, including Node.js and associated backend frameworks, and confidence contributing to clean, maintainable codebases.
• Practical experience integrating large language models into real applications, using APIs such as OpenAI, Anthropic or similar, with an understanding of prompt design, evaluation and operational trade-offs.
• Confidence designing and working with APIs and backend services, including RESTful architectures and integration patterns that support reliability and scale.
• Familiarity with cloud-native environments and production tooling, including containerisation, monitoring and deployment practices, ideally within AWS-based ecosystems.
• Experience working with data stores such as PostgreSQL, MongoDB and or vector databases, with an understanding of how data design supports AI driven use cases.
• The ability to reason about cost, latency, privacy and risk when designing AI powered systems, and to make pragmatic engineering decisions within real-world constraints.
• Strong problem solving skills and attention to detail, with a mindset oriented toward iteration, evidence and continuous improvement.
• The ability to communicate complex technical concepts clearly and simply to a range of audiences, from engineers to product partners and non-technical stakeholders.
• Curiosity and adaptability, with a genuine interest in staying current with emerging AI tools, techniques and best practices, and applying them thoughtfully rather than reactively.
• A collaborative approach and empathy for users and teammates, contributing positively to a team environment and shared ownership of outcomes.
• We encourage applications from people who want to grow into this role and welcome those who bring diverse perspectives, career paths, and experiences.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.