Applied AI Engineer

About the role

We are partnering with a well‑funded, stealth AI startup that is building a next‑generation AI assistant to help users manage everyday tasks, conversations and workflows. The product is pre‑launch, offering a genuine 0‑to‑1 opportunity to join a small, high‑calibre engineering team and influence both product and technical direction from the outset.

Key responsibilities

• Design, develop and ship AI features from concept through production.
• Create and refine agent workflows, prompts, memory handling and tool integration.
• Build reliable, low‑latency AI systems that solve real user problems.
• Improve production performance, reliability and latency of AI services.
• Develop evaluation frameworks to measure real‑world model quality.
• Collaborate closely with product and engineering teams to turn ambiguous problems into working software.
• Contribute to shaping technical direction as the product evolves.

Required profile

• Commercial experience building production AI/ML applications.
• Strong Python engineering skills.
• Hands‑on experience with modern large language models (LLMs) and agentic AI systems.
• Experience with retrieval‑augmented generation (RAG), vector databases and LLM orchestration.
• Proven ability to deploy and operate production ML systems.
• Comfortable working across models, infrastructure and product in fast‑moving, early‑stage environments.

Required skills

• Python
• PyTorch
• JAX
• vLLM
• Vector Databases
• Modern Agent Frameworks
• Retrieval‑Augmented Generation (RAG)
• LLM orchestration
• Production ML deployment

What we offer

• Competitive salary ranging from £80,000 to £180,000 per year plus equity.
• Fully remote work across Europe.
• Opportunity to shape a cutting‑edge AI assistant from the ground up.