AI Engineer

AI Engineer - Feature Prototyping

We are building Conversational AI products powered by large language models, and we are always striving to provide the best features for our clients. This means there’s always a new problem to solve, a new solution to find, and a new way to translate LLM capabilities into real product features.

We are hiring an AI Engineer to help bring these new products to life.

You will sit on our LLM AI team, bridging the gap to our software engineering teams, turning model capabilities into working prototypes and clear reference implementations that can later be built into production systems.

Your work will define how LLMs are actually used across our products. You will take ideas and turn them into real, testable systems that engineers can rely on.

What you will do

• Improve the quality of conversational AI features by making them more accurate, consistent, and responsive through hands-on prototyping
• Work closely with the LLM team to understand how the models behave, where they perform well, and where they break, and to experiment with new features and methods
• Build working prototypes that show how LLM-powered features should function in real product flows
• Design and test prompt structures, input and output formats, and interaction patterns such as retrieval-based systems and agent-style workflows
• Create reference implementations, such as APIs or small services, that give engineering teams something concrete to build from
• Turn high-level product ideas into clear and testable systems
• Identify edge cases, failure points, and user experience issues early through hands-on prototyping
• Work closely with frontend and backend engineers to ensure that what is designed can be built and scaled properly

What we are looking for

• Someone who enjoys turning ideas into working systems
• Someone passionate about Conversational AI
• Comfortable writing code and building prototypes quickly, most commonly in Python
• Experience working with large language models in real applications
• Understanding of how these models behave in practice, including limitations such as inconsistency, latency, and unexpected outputs
• Ability to design systems that work around these limitations
• Product-minded, with the ability to think about how something works for a user, not just in isolation

Backgrounds that tend to fit well

• Data scientists who have moved into LLM or applied AI work
• Physics, maths, or other quantitative science backgrounds with strong coding skills (PhD or industry)
• Machine learning engineers with product exposure
• Applied AI or LLM engineers
• Backend engineers who have worked closely with LLM-based features