Senior AI Engineer

YNH; Greater London; On-site; GBP 90,000 - 120,000; Full time

Job summary

YNH, a venture-backed B2B SaaS company building an AI-native automation platform for the financial services sector, seeks a Senior AI Product Engineer to design, build and scale AI-powered features. You will work on production-grade AI systems that interact with real data, make decisions and execute workflows, not just prototypes.

You’ll own AI features from design through production, collaborating with a small engineering team to embed AI across the platform, improving accuracy, reliability and

Qualifications

• Proven backend/software engineering experience.
• Commercial experience deploying LLM-powered apps.
• Hands-on with LLM APIs (OpenAI/Anthropic).
• Strong API design and distributed systems knowledge.
• Experience with production AI, latency and cost considerations.

Responsibilities

• Build AI agents to investigate issues and execute workflows.
• Develop backend services, APIs, and integrations to connect AI with external platforms.
• Design LLM orchestration, retrieval, and evaluation infra.
• Build systems combining LLM reasoning with structured data and business logic.
• Improve AI accuracy, reliability, and performance.
• Optimize inference latency and operating costs.
• Develop safeguards, approvals, and audit trails for AI actions.
• Own AI features from design to production and iterating.

Skills

Software engineering

LLM deployments

LLM APIs

LLM orchestration

RAG architectures

API design

Distributed systems

Production AI

Product mindset

Tools

OpenAI API

Anthropic API

Job description

We're working with a venture-backed B2B SaaS company building an AI-native automation platform for the financial services industry.

Financial institutions still rely on fragmented systems, manual processes and large operational teams to manage everything from onboarding and compliance to transaction investigations and internal approvals.

This company is building the infrastructure to change that.

Their platform connects directly into existing financial systems, bringing together data, business logic and AI agents capable of understanding complex requests, investigating issues and executing workflows that would traditionally require significant human involvement.

Think intelligent agents that can investigate payment discrepancies, retrieve information across multiple systems, coordinate approval processes and automate operational tasks while maintaining the auditability and control required in regulated environments.

The business has an established product, a growing customer base and a small, highly capable engineering team. They're now investing heavily in the next generation of AI capabilities.

The Role

They're looking for a Senior AI Product Engineer to design, build and scale AI-powered features that solve real operational problems.

This isn't a research role or an opportunity to spend months experimenting with prototypes.

You’ll be building production-grade AI systems that interact with real data, make decisions and execute workflows, where reliability, accuracy and performance genuinely matter.

You’ll have significant ownership across backend engineering, LLM infrastructure and product development, working closely with a small engineering team to shape how AI is embedded throughout the platform.

What You’ll Be Doing

• Building AI agents capable of investigating issues, interpreting data and executing multi-step workflows.
• Developing backend services, APIs and integrations connecting AI systems to external platforms.
• Designing LLM orchestration, retrieval and evaluation infrastructure.
• Building systems that combine LLM reasoning with structured data and deterministic business logic.
• Improving AI accuracy, reliability, observability and performance.
• Optimising inference latency, model selection and operating costs.
• Developing safeguards, approval mechanisms and audit trails for AI-driven actions.
• Taking ownership of AI features from initial design through to production and continuous improvement.

What We’re Looking For

• Strong software engineering background, ideally within backend or product engineering.
• Commercial experience building and deploying LLM-powered applications into production.
• Hands-on experience with LLM APIs, including OpenAI or Anthropic.
• Experience with LLM orchestration, evaluation and performance optimisation.
• Understanding of RAG architectures, retrieval systems and data pipelines.
• Strong foundations in API design, backend architecture and distributed systems.
• An appreciation of the practical challenges of production AI, including hallucinations, latency, reliability and cost.
• A product mindset and the ability to identify where AI creates genuine commercial value.

Experience building AI agents or agentic workflows would be particularly valuable.

We're especially interested in engineers who have moved beyond proof-of-concept AI and have personally shipped systems that real users depend on.

Why It’s Interesting

AI with real responsibility.

Challenging engineering problems.

Significant ownership.

Small team, big technical ambition.

Production AI, not experimentation.

If you’re an experienced software engineer who has already delivered AI applications into production and wants to work on more ambitious agentic systems, we’d be interested in speaking.