Applied AI Engineer

Lumora Solutions; United Kingdom; On-site; GBP 90,000 - 150,000; Full time

Job summary

Lumora Solutions is seeking a Senior Applied AI Engineer to join its AI Platform Engineering Team in the United Kingdom. You will help build the AI runtime, retrieval, guardrails, and evaluation that underpin production-grade AI features.

You will ship production AI agents, optimize for latency and cost, and work with customers to validate outcomes and scale successful solutions. This role offers opportunities to lead, mentor and drive engineering excellence within a fast-growing software

Qualifications

• Experience shipping LLM/ML-backed software into production, including agentic and RAG systems.
• Strong programming skills in Python or C#/.NET with understanding of orchestration and production failure modes.
• Experience building evaluation frameworks and quality controls to measure model and agent performance.
• A cost- and latency-conscious mindset balancing technical quality with reliability and business value.

Responsibilities

• Build and optimise production AI agents, including orchestration, tool calling, model selection and RAG.
• Develop evaluation frameworks, safety guardrails and automated QA for reliable AI systems.
• Own production performance, balancing latency, cost, reliability and measurable business impact.
• Collaborate with product teams and customers to validate outcomes and scale solutions.
• Shape engineering practices, mentor others and foster technical excellence.

Skills

LLM/ML production

Python/.NET (C#)

Agent orchestration

RAG systems

Evaluation frameworks

Quality controls

Latency & cost awareness

Tools

Python

C#/.NET

Job description

Our client is a fast-growing software technology firm in the transportation sector, looking for a Senior Applied AI Engineer to join its AI Platform Engineering Team.

As a founding team member, you will build the AI runtime, retrieval, guardrails, and evaluation that make the platform's AI features work in production.

What you will be doing:

• Build and optimise production AI agents, including orchestration, tool calling, model selection and RAG.
• Develop evaluation frameworks, safety guardrails and automated QA to ensure reliable, high-quality AI systems.
• Own production performance, balancing latency, cost, reliability and measurable business impact.
• Work closely with product teams and customers to validate outcomes, prove value and scale successful solutions.
• Shape engineering best practices, mentor others and help build a culture of technical excellence and pragmatic delivery.

What you will bring:

• Proven experience shipping LLM or ML-backed software into production, including agentic and RAG systems.
• Strong Python or C#/.NET skills, with a solid understanding of agent orchestration and production failure modes.
• Experience building evaluation frameworks and quality controls to measure model and agent performance.
• A cost- and latency-conscious mindset, balancing technical quality with reliability and business value.
• Join a fast-growing Software Technology Company.
• Clear opportunities to grow, take ownership, and progress within the company.