Artificial Intelligence Engineer

Wave Group; Greater London; Hybrid; GBP 60,000 - 90,000; Full time

Benefits offered by this job

Equity

Job summary

Wave Group in London is seeking a mid-level to senior engineer to own end-to-end LLM-powered features. You will design, build, and ship features using model APIs, focusing on retrieval over structured data, agents and tool use, guardrails, and evals.

You’ll work with a senior ML engineer and contribute to product decisions. The role emphasizes hands-on implementation, user-facing decisions, and a startup mindset, with on-site work four days a week and Fridays from home.

Qualifications

• 2+ years building LLM products used by real customers.
• Hands-on with model APIs, retrieval, tool use and prompt design.
• Experience measuring quality via evals, monitoring, and iteration.
• Startup experience or strong interest in early-stage ownership.
• Strong product sense and willingness to talk to users.
• UK right to work; sponsorship not available.

Responsibilities

• Design, build and ship LLM-powered features used by real customers.
• Build retrieval and tool-use systems over structured data.
• Define and run evaluations, and monitor quality, latency and cost in production.
• Iterate on features based on user feedback and usage data.
• Work with product and data colleagues to decide what to build next.

Skills

LLM product development

Model API usage

Evaluation & monitoring

Product sense

User feedback adaptation

Startup experience

Job description

London, on-site four days a week (Fridays from home) · Full-time · Mid-level to senior

£60,000 to £90,000 base, plus equity for all employees

About the company

We're working with a London startup of around 25 people building a data product in the investments space. Their AI features surface insight from that data directly to users, and they're used daily. The company is early enough that every engineer shapes what gets built, and we're scaling the product quickly.

About the role

You'll own LLM-powered features end to end, from evaluation design through to production. The work is built on model APIs rather than model training. You'll focus on retrieval over structured data, agents and tool use, guardrails, and evals, and you'll ship changes based on how users actually use the product.

You'll work closely with the senior ML engineer and contribute directly to product decisions.

What you'll do

• Design, build and ship LLM-powered features used by real customers
• Build retrieval and tool-use systems over structured data
• Define and run evaluations, and monitor quality, latency and cost in production
• Iterate on features based on user feedback and usage data
• Work with product and data colleagues to decide what to build next

What we're looking for

• Two or more years building LLM products that real users rely on
• Hands-on experience with model APIs, including retrieval, tool use and prompt design
• A habit of measuring quality through evals, monitoring and iteration
• Startup experience, or a clear preference for early-stage ownership
• Strong product sense and a willingness to talk to users
• Full UK right to work (sponsorship isn't available for this role)