> Markdown version of [/jobs/ext/2065598-senior-software-developer-mcp-ai](https://www.wearedevelopers.com/jobs/ext/2065598-senior-software-developer-mcp-ai). 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). --- # Senior Software Developer, MCP/AI - **Company:** Autodesk - **Location:** San Rafael, CA, United States (Remote available) - **Experience:** Expert - **Salary:** $123,000.0 - **Contract:** Permanent contract - **Skills:** JavaScript (Programming Language), Computer-Aided Design, 3D Visualization, Application Programming Interfaces (APIs), Agile Methodology, Artificial Intelligence, Amazon Web Services, Automation of Tests, Cloud Engineering, Code Review, Computer Engineering, Continuous Integration, Distributed Systems, Machine Learning, Node.Js, Service-Oriented Architecture, TypeScript, WebGL, Datadog, ReactJS, Large Language Models, Multi-Agent Systems, Git Flow, Information Technology, Web Technologies, Autodesk Autocad, Docker - **Published:** August 15, 2026 - **Apply:** https://arc.dev/remote-jobs/j/redirect/pb8x2zqwi2 ## About the Role As a Senior MCP/AI Developer, you will own agentic subsystems end-to-end - from problem clarification and design through implementation, evaluation, deployment, and production support. You'll design how agents orchestrate tools, retain context across sessions, and retrieve the right information (RAG), and you'll define how we measure their quality. You bring solid applied-ML literacy and the engineering judgment to ship AI systems that are reliable, fast, and trustworthy, while mentoring engineers and contributing to platform architecture., * Bachelor's or Master's in Computer Science / Computer Engineering, or equivalent experience * 5+ years delivering production-grade software * Strong proficiency in TypeScript/JavaScript and modern web technologies (e.g. React) * Demonstrated experience building AI/ML-powered features - LLMs, agents, orchestration RAG systems, or similar - in production * Applied ML literacy: prompt/agent design, retrieval, and evaluating model/agent behavior * Solid understanding of distributed systems, APIs, and service-oriented architectures * Hands-on with automated testing, CI/CD, and Git workflows; effective communication in English; experience in Agile environments, * Familiarity with the Model Context Protocol (MCP), agent frameworks, or composable tool/capability architectures * Experience with vector stores, embeddings, and RAG at production quality * Node.js and cloud-native architectures (AWS, Docker); observability tooling * Experience contributing to platform-level or cross-team technical initiatives * Familiarity with 2D/3D visualization, CAD/BIM, or graphics technologies (WebGL/WebGPU) The Ideal Candidate You are a strong hands-on developer who owns systems end-to-end and brings real applied-ML judgment - you know how to make an agentic feature reliable, not just demo-able. You design scalable solutions, make sound trade-offs, evaluate rigorously, and mentor others. You communicate clearly across disciplines and are motivated by building trustworthy agentic capabilities that power real customer workflows. ## Description Autodesk's Visualization Solutions power high-performance 2D and 3D visualization experiences across our product portfolio. Our new team in Canada is bringing agentic AI to that experience - expanding our Viewer MCP (Model Context Protocol) into a production-grade agentic platform that lets users interact with their models in natural language and automate complex visualization and data tasks., * Design and implement complex agentic subsystems: tool/capability composition, agent * Orchestration, context retention across sessions, and retrieval (RAG) * Own subsystems end-to-end - clarify requirements, design, implement, evaluate, deploy, and support in production * Build and own evaluation for AI behavior - quality, safety, latency, and cost - and use it to drive durable improvements * Embed trust into agentic workflows: human-in-the-loop review gates, traceability, reversibility, and confidence signaling * Make sound trade-offs across model choice, prompting/orchestration, and system design, balancing accuracy, latency, cost, and maintainability * Contribute to the architecture and cross-product integrations of the agentic platform * Lead root-cause analysis for production issues; elevate quality through code review, automated testing, and CI/CD * Partner with Product, UX, QA, and other Visualization Solutions teams to turn customer workflows into robust technical solutions; mentor developing developers, * Connaissance du Model Context Protocol (MCP), des frameworks d'agents ou des architectures d'outils/capacités composables * Expérience avec les magasins de vecteurs, les embeddings et le RAG à un niveau de qualité de production * Node.js et architectures cloud-native (AWS, Docker) ; outils d'observabilité * Expérience dans la contribution à des initiatives techniques au niveau de la plateforme ou inter-équipes * Connaissance de la visualisation 2D/3D, de la CAO/BIM ou des technologies graphiques (WebGL/WebGPU) Le Candidat Idéal Vous êtes un développeur chevronné et pragmatique qui maîtrise les systèmes de bout en bout et fait preuve d'un véritable sens pratique en matière d'apprentissage automatique appliqué - vous savez comment rendre une fonctionnalité d'agent fiable, et pas seulement présentable en démonstration. Vous concevez des solutions évolutives, effectuez des compromis judicieux, procédez à des évaluations rigoureuses et encadrez vos collègues. Vous communiquez clairement avec les différentes disciplines et êtes motivé par la création de capacités d'agents fiables qui alimentent les véritables flux de travail des clients. ## Related Videos - [Watch Tests Go Brrrr! : Getting Started with Cypress in ReactJS](https://www.wearedevelopers.com/videos/282-watch-tests-go-brrrr-getting-started-with-cypress-in-reactjs) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Rendering Design Software in the Browser at Penpot](https://www.wearedevelopers.com/videos/1353-rendering-design-software-in-the-browser-at-penpot) - [API, MCP or MCP App? Choosing the right surface for AI agents](https://www.wearedevelopers.com/videos/100305-api-mcp-or-mcp-app-choosing-the-right-surface-for-ai-agents) - [Docker build without Docker](https://www.wearedevelopers.com/videos/100114-docker-build-without-docker) - [Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding](https://www.wearedevelopers.com/videos/1604-supercharge-agentic-ai-apps-a-devex-driven-approach-to-cloud-native-scaffolding) ## Related Articles - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [Everything a Developer Needs to Know About MCP with Neo4j](https://www.wearedevelopers.com/magazine/604-everything-a-developer-needs-to-know-about-mcp-with-neo4j) - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [Dev Digest 164: AI Agents, AI Blindspots and MCP security problems](https://www.wearedevelopers.com/magazine/578-dev-digest-164-ai-agents-ai-blindspots-and-mcp-security-problems) - [What is Software Engineering in the Age of AI?](https://www.wearedevelopers.com/magazine/640-what-is-software-engineering-in-the-age-of-ai)