Senior AI Platform Engineer

9fin operates at the center of global debt markets, the largest asset class exceeding $145 trillion in value. The current infrastructure for these markets relies on disconnected data, PDF documents, and manual procedures. 9fin provides a single platform that unifies proprietary credit data, deep analysis, and high-value workflows for these markets. The company currently serves over 300 leading institutions globally, including major banks, asset managers, private equity firms, law firms, and advisory firms. Growth in the United States is rapid, and retention is excellent due to strong adoption of core workflows. The company is approaching a significant transition. With confirmed product-market fit and strong global demand, 9fin is advancing toward becoming the definitive platform for debt markets worldwide. THE OPPORTUNITY The AI Engineering team at 9fin is creating the next generation of AI capabilities that will power future products. The company is seeking a Senior AI Platform Engineer to participate in designing, building, and evolving the core AI platform that supports Generative AI, Agentic AI, and machine learning applications across the business. This role offers the chance to join at the platform's inception. Instead of inheriting a finished system, you will help shape its architecture, define engineering standards, and construct reusable infrastructure that allows AI teams to move quickly, safely, and at scale. Working with backend engineers and AI engineers, you will create shared platform services that power functions ranging from intelligent document understanding to autonomous AI agents. These agents will be capable of running scheduled workflows, generating morning briefings, identifying distressed companies, and supporting future AI-powered product experiences. Every day is different, but here is an example of the kind of work you will do. Design, build, and continuously evolve the enterprise AI platform that powers AI products across 9fin. Develop scalable AI services supporting Agentic AI, Retrieval-Augmented Generation (RAG), embeddings, vector search, model serving, and intelligent automation. Build orchestration layers that transform structured and unstructured enterprise data into reusable AI capabilities. Develop production-ready AI applications using modern LLM frameworks and orchestration tools. Design reusable platform components for prompt management, model serving, vector search, embeddings, AI gateways, and evaluation services. Build APIs, SDKs, and developer tooling that enable self-service AI development across engineering teams. Design secure, scalable deployment pipelines for AI models and applications. Build AI observability capabilities including monitoring, tracing, evaluation, cost optimisation, and production quality measurement. Collaborate closely with AI Engineers, Backend Engineers and Engineering Leadership to define platform architecture and engineering standards. Establish engineering best practices around testing, governance, Responsible AI, deployment, and operational excellence. Continuously evaluate emerging AI technologies and evolve the platform as the ecosystem rapidly advances. WHAT MAKES THIS ROLE DIFFERENT This role differs from many AI Platform positions because it focuses on building the platform from the ground up. You will join at an early stage when many architectural decisions have not yet been made, giving you real influence over how AI is built, deployed, and operated across 9fin. Within your first six months, you will help build the platform that powers production AI agents capable of running autonomously in the background. These agents will support workflows such as scheduled market briefings, distressed company discovery, and future intelligent financial research products. Instead of owning a single AI product, you will build shared capabilities that enable multiple engineering teams to rapidly develop, deploy, and operate AI solutions at scale. You will be one of a small number of senior engineers helping shape the technical direction of the platform alongside the Engineering Lead and fellow senior engineers. ABOUT YOU This role is a great fit if you meet the following criteria. AI PLATFORM ENGINEERING Have 5+ years of software engineering experience, including 2+ years building AI/ML platforms, Generative AI applications, or production machine learning systems. Have experience designing and deploying enterprise AI applications into production with a strong focus on scalability, reliability, and developer experience. LLMS & AGENTIC AI Have hands-on experience building applications powered by Large Language Models (LLMs). Have experience building Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG) solutions, making use of embeddings, vector databases, and modern LLM orchestration. DRAFT TO REPLACE: About the role You will architect and ship the core AI platform for 9fin. This role owns the foundational systems that enable Generative AI and Agentic AI workflows. You will define standards that allow rapid, safe scaling. Your work directly supports global debt markets infrastructure. Key facts

Location: UK

Engagement: Full-time

Compensation: £130,000 to £160,000 per year What you'll do Architect reusable platform services for document understanding and autonomous agents. Design secure deployment pipelines ensuring safe production rollout for AI models. Develop APIs and SDKs that let engineering teams build AI features independently. Implement observability frameworks tracking cost, quality, and tracing for production AI. Evaluate and integrate emerging AI tools to keep platform capabilities current. Build vector search and embeddings workflows for enterprise data retrieval. Establish testing and governance standards aligned with Responsible AI practices. Create prompt management systems enabling efficient model experimentation. Orchestrate structured and unstructured data into reusable AI capabilities. Support scheduled workflows like morning briefings and distressed company discovery. Requirements You must possess over five years writing software, including two years with AI platforms. You need hands-on experience deploying enterprise Generative AI applications at scale. You understand Large Language Models and the Model Context Protocol deeply. You have built Retrieval-Augmented Generation solutions using vector