AI Tooling Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Tooling Engineer based in France. We are looking for an AI Tooling Engineer to develop and scale an internal agentic platform that brings together company knowledge, data, and tools in one secure, accessible environment. Working closely with a Principal Engineer, you will build production-ready AI agents and integrations that help employees and their AI assistants access the information they need. You will take ownership of the full development lifecycle, from understanding user needs and designing solutions to deployment, monitoring, and continuous improvement. Using technologies such as Python, LangGraph, LLM APIs, and Model Context Protocol (MCP), you will transform prototypes into reliable tools used across the organization. You will also establish evaluation frameworks, optimize AI performance and costs, and ensure robust security and access controls. This remote opportunity offers the chance to shape company-wide AI capabilities within a globally distributed, technology-driven team.

You will help develop and maintain an internal AI platform, combining agent development, systems integration, production engineering, and continuous optimization to deliver practical tools that improve how teams work. Collaborate with the Principal Engineer to design, develop, and deploy new platform capabilities, taking ownership from initial design through production release. Integrate internal systems and SaaS applications by connecting APIs and data sources, defining shared data models, and implementing appropriate access permissions. Build AI agents and supporting tools, including MCP servers that enable agents across the organization to interact with internal systems and retrieve relevant context. Design and improve retrieval workflows, tool calling, embeddings, prompts, and context management to deliver accurate and useful AI-generated responses. Establish and maintain AI quality standards through evaluation datasets, benchmarks, regression testing, tracing, and observability. Monitor performance indicators, including cost per answer and token usage, and optimize models, prompts, and workflows for efficiency and reliability. Troubleshoot production issues, incorporate user feedback, and continuously improve the platform based on real-world usage. Turn proofs of concept into secure, scalable cloud applications with appropriate infrastructure, deployment processes, and identity and access controls. Use AI coding agents as a core part of the development workflow while maintaining code quality through clear specifications, automated tests, reviews, and sound engineering practices. Contribute to company-wide AI tooling initiatives, including evaluating and standardizing internal AI tools, tracking usage and costs, and defining standards for AI-generated applications. Support other teams in adopting and building on the platform, helping them develop effective AI-powered workflows and internal applications. Engage with technical and non-technical stakeholders across the organization to understand their needs, prioritize improvements, and communicate solutions clearly. Requirements: The ideal candidate is a hands-on software engineer with practical experience delivering AI agents to production, a strong understanding of modern AI development frameworks, and the ability to build secure, reliable internal tools. At least 3 years of experience building and shipping production software, primarily using Python and relational databases. Proven experience building and deploying at least one production AI agent with LangGraph that is used by real users. Practical expertise in agent development, including tool calling, retrieval and embeddings, prompt engineering, and context design. Hands-on experience with LLM APIs from major providers, including token management and cost optimization. Experience working with MCP or comparable tool protocols, both as a server and as a client. Strong understanding of AI evaluation methodologies, including test datasets, LLM-as-judge approaches, regression testing, and performance monitoring. Familiarity with tracing and observability tools such as Langfuse or equivalent solutions. Experience integrating APIs and data sources, including SaaS applications, SQL databases, and data warehouses. Practical experience with cloud infrastructure on Google Cloud Platform (GCP), Amazon Web Services (AWS), or both, including containers, managed databases, identity and access management, and CI/CD pipelines. Daily use of AI coding agents, with the ability to validate their output and maintain high standards of software quality. Strong understanding of security principles, identity management, permissions, and least-privilege access controls. Experience with version control and collaborative development tools such as GitHub or Bitbucket. Excellent written and spoken English, with the ability to communicate technical concepts clearly to both technical and non-technical audiences. Desired Skills: Familiarity with web data extraction, web scraping, or related technologies. Experience with Django and PostgreSQL, including vector search using pgvector. Frontend development skills sufficient to build and maintain chat interfaces using React or Next.js. Experience developing internal tools that achieve adoption among colleagues. Familiarity with semantic layers, knowledge graphs, or structured representations of organizational knowledge. Experience implementing agent memory, multi-agent architectures, or advanced agent orchestration. Previous experience working with remote, globally distributed teams. Benefits: Fully remote work, offering flexibility in where you work. Opportunity to join a self-motivated, progressive, and multicultural team. Hands-on experience with cutting-edge AI technologies, open-source frameworks, and modern software development tools. Opportunity to shape and develop AI tooling used across the organization. End-to-end ownership of meaningful engineering projects, from initial design to production deployment and ongoing optimization. Collaborative environment focused on innovation, autonomy, and continuous improvement.