LLM Application Engineer

About the role

We are looking for an LLM Application Engineer to help build the intelligence layer behind an AI-powered product.

This role sits at the intersection of large language models, software engineering and product development. You'll turn LLM capabilities into practical features and reliable AI experiences that work beyond simple chat interactions.

You'll take ownership of AI problems from understanding user needs and designing agent workflows through model and tool integration, evaluation and continuous improvement in production.

What you'll do

• Build and ship LLM-powered applications and AI agent workflows
• Design systems that support reasoning, planning, memory, tool usage and multi-step execution
• Develop orchestration layers that transform probabilistic model outputs into predictable, observable and safe actions
• Connect LLMs with APIs, databases, search systems, internal services and external tools
• Improve model behaviour through prompt engineering, context engineering, structured outputs and tool calling
• Create evaluation frameworks and datasets to measure AI quality, reliability and regressions
• Diagnose issues across the entire AI stack — from prompts and model behaviour to orchestration, backend services and product UX
• Optimise AI systems for quality, latency and cost
• Work closely with product and engineering teams to turn ambiguous challenges into practical AI solutions
• Establish production practices around observability, tracing, experimentation, evaluation and continuous improvement

How we work

You'll work in a highly hands-on environment where engineers are expected to take ownership of problems end-to-end.

The team moves quickly, experiments continuously and focuses on turning new AI capabilities into products that work reliably in real-world scenarios. You'll need to be comfortable operating in areas where the technology and requirements are evolving rapidly, while maintaining a strong focus on engineering quality and measurable outcomes.

In this role, you'll help turn emerging LLM capabilities into dependable product functionality. Success means: AI features move efficiently from concept to production and measurable user impact; LLM-powered workflows are reliable, scalable, observable and maintainable; AI quality improves through systematic evaluation, experimentation and iteration; Agent workflows become increasingly predictable, efficient and cost-effective; Complex AI capabilities are transformed into simple and intuitive experiences for users.

Tech stack

• Python
• LLM APIs and model providers, including OpenAI-compatible APIs and open-weight models
• Agent frameworks and orchestration systems
• Vector databases and retrieval systems
• Backend services, APIs and distributed systems
• PyTorch / JAX

What we're looking for

We're looking for someone with:

• Strong software engineering fundamentals and experience building AI-powered applications
• Hands-on experience working with LLMs, generative AI or agent-based systems
• Practical experience designing prompts, AI workflows, evaluation methods or model behaviour
• The ability to write clean, production-ready code
• Comfort working across different layers of the stack — from models and AI systems to the final product
• Strong problem-solving skills, particularly when dealing with ambiguous or rapidly changing challenges
• A strong bias toward shipping, experimentation and continuous improvement