Staff AI Engineer: LLMs & Agentic Systems Lead

Dex; United Kingdom; Sur place; GBP 140 000 - 190 000; Plein temps

Résumé du poste

Dex, in partnership with clients, is hiring a Staff AI Engineer to shape how LLMs and agentic systems are applied across the product, from prototyping intelligent workflows to building natural language interfaces. You'll own end-to-end AI initiatives in a regulated domain, define playbooks, design backend AI services, and drive evaluation pipelines to ensure accuracy and safety.

This role demands hands-on expertise with LLMs, RAG architectures, and a strong product sense to communicate AI

Qualifications

• 5+ years building customer-facing products with end-to-end ownership.
• Hands-on experience with LLMs, prompt engineering, and agent frameworks.
• Production experience with RAG architectures.
• Ability to design and implement evaluation pipelines for AI models.
• Strong product instincts and ability to articulate AI decisions commercially and technically.

Responsabilités

• Define the AI strategy and roadmap, identifying high-leverage applications for LLMs and agentic systems across the product.
• Design and build backend services for AI workflows, from prototypes to production-ready systems.
• Develop and optimise prompt engineering strategies for complex tax compliance scenarios.
• Build robust evaluation pipelines to ensure model accuracy, safety, and reliability in a regulated domain.
• Architect and implement internal and customer-facing agent platforms.

Connaissances

LLMs

Prompt engineering

Agent frameworks

RAG architectures

Evaluation pipelines

Description du poste

Dex, in partnership with clients, is hiring a Staff AI Engineer to shape how LLMs and agentic systems are applied across the product, from prototyping intelligent workflows to building natural language interfaces. You'll own end-to-end AI initiatives in a regulated domain, define playbooks, design backend AI services, and drive evaluation pipelines to ensure accuracy and safety.

This role demands hands-on expertise with LLMs, RAG architectures, and a strong product sense to communicate AI