About the role
We’re looking for a hands-on engineer who builds production AI systems end to end. You’ll design multi-agent backends, RAG pipelines and MCP servers, and ship the full-stack platforms around them for enterprise clients in financial services.
What you’ll do
• Build things (with or without AI as you want)
• Be able to read codes and understand codes and it's use, really well.
• Build multi-agent LLM systems using Azure OpenAI, Gemini/ADK or similar frameworks
• Design RAG pipelines: document ingestion, OCR, embeddings and vector search
• Build and deploy MCP servers for tools like Claude, VS Code Copilot and enterprise clients
• Develop full-stack apps with Angular, Node.js/TypeScript and Python (FastAPI)
• Integrate enterprise systems (CRM, Microsoft Graph, Databricks) with secure Entra ID auth
• Own CI/CD, containerization and Azure deployments
What you bring
• 6+ years in full-stack development,
with at least 1–2 years building production LLM applications
• Robust Node.js/TypeScript and Python; C#/.NET is a plus
• Hands-on Azure experience (OpenAI, Functions, Container Apps, Cosmos DB, DevOps)
• Experience with vector databases (MongoDB Atlas, Cosmos DB or similar)
• Comfortable with async architectures: Redis streams, queues, SSE/WebSockets
• Proven ability to work independently in a remote, distributed team
Nice to have
• Financial services or private equity domain exposure
• Agentic AI frameworks (ADK, LangGraph, Semantic Kernel)
• Open-source contributions
Why Tytan
• Work on real agentic AI products for enterprise clients, with ownership from architecture to production.
Apply through LinkedIn with your resume and a link to something you’ve built.