Applied AI Engineer

WeDoTech; Greater London; Hybrid; GBP 84,000 - 140,000; Full time

Job summary

WeDoTech in London is seeking a Senior Applied AI Engineer to own production LLM systems, focusing on real-world problems and scalable deployments. You will collaborate with Product to improve quality, cost and latency, and shape new features for a production-ready AI platform.

The role emphasizes hands-on engineering, AI-native tooling, and delivering robust, production-grade solutions in a hybrid London office environment.

Qualifications

• 4+ years of experience building production software.
• Experience shipping LLM-powered systems used by real users.
• Hands-on in RAG, prompting and/or agents.
• Strong production engineering fundamentals: reliability and incident response.
• Good technical understanding of LLMs: sampling parameters and embeddings.
• Experience designing meaningful evaluations for AI/LLM systems.
• Comfortable using agentic tooling like Claude Code, Codex or similar.
• Experience working and shipping at pace.
• Strong communication skills to explain technical decisions clearly.

Responsibilities

• Build, improve and maintain production LLM systems.
• Improve cost and latency of LLM-powered features without sacrificing accuracy.
• Design evaluation frameworks to measure improvements.
• Investigate production issues, identify root causes and fixes.
• Work across RAG, prompting and agentic systems.
• Collaborate with Product to shape new functionality to production.
• Use Claude Code as part of day-to-day development.
• Make sound engineering decisions under ambiguity.

Skills

Production software

LLM-powered systems

RAG prompting agents

Reliability & incident response

LLMs fundamentals

AI evaluation design

Claude Code / Codex tooling

Communication

Shipping at pace

Tools

Claude Code

Codex

Job description

Job Title: Senior Applied AI Engineer

Salary: Up to £140,000 base

Location: London - Moorgate | Hybrid, 2 days per week in the office

Work Type: Permanent

Role: We're working with an exciting AI technology business looking for a Senior Applied AI Engineer to join the team building and improving its production LLM systems. This is a hands-on engineering role for someone who wants to work on real-world AI problems where the technology is already being used in production. Rather than focusing on training models or open-ended research, you'll be solving the challenges that come with making LLM-powered products genuinely work at scale. You'll have the opportunity to influence how the product evolves, working closely with Product to improve quality, reduce cost and latency, build better evaluation frameworks and solve real production failures. The engineering environment is also heavily AI-native, with tools such as Claude Code forming a key part of how the team builds and ships software.

Responsibilities:

• Build, improve and maintain production LLM systems
• Improve the cost and latency of LLM-powered features without sacrificing accuracy
• Design and implement evaluation frameworks that can reliably measure whether changes genuinely improve the product
• Investigate production failures raised by analysts, identify root causes and implement effective fixes
• Work across areas including RAG, prompting and agentic systems
• Partner closely with Product to shape new functionality and take ideas through to production
• Use AI-native engineering tools such as Claude Code as part of your day-to-day development workflow
• Make sound technical decisions when working through ambiguous engineering problems

Required Skills:

• 4+ years of experience building production software
• Experience shipping LLM-powered systems that have been used by real users
• Hands-on experience across areas such as RAG, prompting and/or agents
• Strong production engineering fundamentals, including an understanding of reliability and incident response
• Good technical understanding of LLMs, including concepts such as sampling parameters and embeddings
• Experience designing meaningful evaluations for AI/LLM systems
• Comfortable using agentic development tooling such as Claude Code, Codex or similar
• Experience working and shipping at pace
• Strong communication skills with the ability to explain technical decisions clearly and concisely

Why should I apply?

This is an opportunity to move beyond LLM prototypes and work on the difficult engineering problems that appear when AI systems are operating in a real production environment. You'll be able to see the impact of your work directly – whether that's improving the quality of outputs, making the platform faster and more cost-effective, solving production issues or influencing what gets built next. You'll also be joining an engineering environment that actively embraces AI-native development rather than simply experimenting with it on the side. If you're an experienced software engineer who has already shipped LLM systems and you want your next role to combine hands‑on engineering, applied AI, product influence and genuine production challenges, this could be a great next step.