AI Engineer (Conversational AI)

General Description

TalentCo are delighted to be partnering with an established PE-backed tech company looking to hire several high-calibre AI Engineer into their UK business, as they build a new Conversational AI platform from the ground up.

The following information aims to provide potential candidates with a better understanding of the requirements for this role.

These hires will be based predominantly from home, with occasional trips to their HQ just north of London, but with plenty of flexibility to suit individual circumstances.

The client are developing a low-code, multi-tenant platform that enables large enterprises to design, build and deploy AI agents capable of handling both single-step LLM tasks and complex multi-step agentic workflows.

As AI Engineer you will:

• Architect and implement the LLM, agentic and RAG modules that power the platform’s low-code environment.
• Build primitives, abstractions and orchestration components that allow clients to construct robust agentic workflows with deterministic and probabilistic behaviours.
• Develop scalable backend services for multi-tenant execution of AI agents, including concurrency management, task routing and resource control.
• Fine tune and evaluate LLMs and SLMs for enterprise use cases such as knowledge automation, summarisation, classification, conversational agents and multi-step reasoning.
• Deploy LLM-based applications and agentic workflows at scale, with practical awareness of compute cost modelling, latency trade-offs, container orchestration and distributed systems patterns.

We want to hear from you if:

• You have 2+ years of hands-on experience building production applications, with at least 1 year as an AI Engineer or ML Engineer shipping AI products and features.
• You’re an expert when it comes to backend development using Python and you’re proficient in modern web technologies, especially TypeScript.
• You have an understanding of AI-powered applications, including LLMs, chat interfaces, and agentic workflows or strong desire to build AI products from scratch.
• Hands-on experience building and deploying LLM-based applications, including knowledge of tokenisation, prompt optimisation, model selection and evaluation methods.
• Strong knowledge of cloud infrastructure (AWS, GCP, or Azure) and scalable architectures. xwzovoh

What do they offer?

• Salary between £90k-£120k
• Comprehensive benefits package
• Remote-first setup with occasional visits to North London HQ
• Work from anywhere policy