> Markdown version of [/jobs/ext/4699449-ai-platform-engineer](https://www.wearedevelopers.com/jobs/ext/4699449-ai-platform-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Platform Engineer - **Company:** Tradeweb - **Location:** London, United Kingdom - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Microsoft Azure, Cloud Computing, Cyber Security, Continuous Integration, Data Integration, Information Leak Prevention, Cursor, Identity and Access Management, Interoperability, Python (Programming Language), Key Management, OAuth, OpenID, Open Web Application Security, Azure Machine Learning, Software Engineering, Datadog, Cloud Platform System, LangChain, Retrieval-Augmented Generation, Large Language Models, Claude Code, Grafana, Google Vertex AI, Llamaindex, AgentCore, Generative AI, AI Coding Agents, Langfuse — LLM Observability and Analytics Platform, AI Platforms, Infrastructure Automation Frameworks, Amazon Bedrock, RAGAS (Retrieval Augmented Generation Assessment), Cloudwatch, Model Context Protocol, OpenAI Codex, GPT, Agent2Agent Protocol - **Published:** November 13, 2026 - **Apply:** https://dejobs.org/x/x/C398ABDD3C13433F9AD95B6DC6C086F9/job/ ## About the Role Essential experience * AI platform engineering: Hands-on experience building and operating production LLM / generative AI platforms. Amazon Bedrock / AgentCore experience is preferred; comparable platforms such as Microsoft Azure AI Foundry or Google Vertex AI are welcome. * Software engineering: Strong software engineering background with proficiency in Python and experience working with LLMs and generative AI. * Agent and data integration: Experience connecting AI applications and agents to tools, APIs and internal data through MCP or comparable integrations, including retrieval-augmented generation (RAG). * Platform operation: Experience managing model access and cost, and evaluating and monitoring AI services for quality, reliability and performance. * AI security: Practical understanding of prompt injection, data leakage and excessive agency, with experience applying access controls, secrets management and auditing. * Cloud delivery: Experience deploying AI services using cloud infrastructure, identity and access management, infrastructure as code and CI/CD. AWS experience is strongly preferred. * Delivery and enablement: Ability to turn internal workflows into working AI solutions, communicate clearly and create reusable components for wider adoption. * AI coding tools: Fluent in AI-assisted development, with hands-on experience configuring and standardizing tools such as Claude Code, Cursor or OpenAI Codex for safe team use. * Agent interoperability and identity: A2A protocols, delegated authorization, OAuth / OIDC and scoped agent credentials. * Frameworks and tooling: Experience with LLM frameworks and evaluation or observability tools, such as LangChain, LangGraph, LlamaIndex, Strands Agents, provider SDKs, Langfuse, OpenTelemetry, CloudWatch or Ragas, or equivalents. * Registries: Experience curating approved MCP server and agent skills registries. * AI security frameworks: Familiarity with the OWASP Top 10 for LLM Applications and applying its guidance. * Financial services: Experience delivering technology in financial services, particularly alongside Risk, Cyber Security, Compliance or Internal Audit. * Certifications and training: Relevant certifications or AI-focused training, such as AWS Solutions Architect - Professional or AWS Machine Learning Engineer - Associate. Desirable experience * Agent interoperability and identity: A2A protocols, delegated authorization, OAuth / OIDC and scoped agent credentials. * Frameworks and tooling: Experience with LLM frameworks and evaluation or observability tools, such as LangChain, LangGraph, LlamaIndex, Strands Agents, provider SDKs, Langfuse, OpenTelemetry, CloudWatch or Ragas, or equivalents. * Registries: Experience curating approved MCP server and agent skills registries. * AI security frameworks: Familiarity with the OWASP Top 10 for LLM Applications and applying its guidance. * Financial services: Experience delivering technology in financial services, particularly alongside Risk, Cyber Security, Compliance or Internal Audit. * Certifications and training: Relevant certifications or AI-focused training, such as AWS Solutions Architect - Professional or AWS Machine Learning Engineer - Associate. ## Description To capitalize on our success and continued growth plans, we are seeking an AI Platform Engineer to help build and scale Tradeweb's enterprise AI capabilities. You will build and run the shared AI platform layer on AWS Bedrock that engineering and business teams use to deliver AI safely and at scale: model gateways, Model Context Protocol (MCP) servers, evaluation and observability tooling, cost controls and secure configuration templates for AI developer tooling. You will also work hands-on alongside internal teams, including Risk, Cyber Security and Internal Audit, to turn their workflows into working AI solutions on the platform. This is not a research role: you will build on foundation models through managed services rather than train models from scratch. As a member of the Technology team, this role will work with subject matter experts across engineering, infrastructure, cloud, data, information security, risk, compliance and the business, and will directly shape how AI is adopted across the firm. The role works closely with our Security Architecture and Cyber Security teams, so a working understanding of application, platform and cyber security is important. We look to hire people who are comfortable working with minimal supervision as part of a team that has consistently delivered ground-breaking and innovative solutions in one of the most exciting and fast-moving areas of the financial markets. We need people who can prioritize, move quickly from idea to production, and effectively articulate complex issues to technical and non-technical team members., * Build and run the AI platform: Develop and operate the shared AI platform on AWS Bedrock and AgentCore, supporting secure, reliable deployment of AI applications and agents. * Manage model access and cost: Maintain a shared model gateway with access controls, approved model configurations, usage monitoring and cost controls. * Embed security and agent identity: Implement security, privacy and responsible AI controls, including agent identities, delegated authorization and auditable access, in line with Security Architecture standards. * Connect agents to tools and data: Build secure MCP integrations and RAG pipelines connecting agents to internal data and APIs, and support approved agent interoperability and tool registries. * Automate platform delivery: Use infrastructure as code and CI/CD to deploy, configure and maintain AI platform services consistently. * Evaluate and monitor AI services: Establish evaluation and observability to track output quality, agent behaviour, reliability, performance and cost. * Enable engineering teams: Provide reusable reference architectures, templates and secure AI coding tool configurations that help teams build and adopt AI solutions. * Deliver solutions with internal teams: Work hands-on with Risk, Cyber Security and Internal Audit to turn workflows into working AI solutions, partnering with Compliance and Legal on relevant requirements.