Job Description

Responsibilities: - Create Agent Tools: Write Python functions and API wrappers that allow our agents to perform actions (e.g., "Look up material price in SAP"), following the MCP standard. - Maintain Quality: Write comprehensive unit tests and "Evals" (using LLM-as-a-Judge) to ensure our agents are accurate, safe, and helpful. - Support Operations: Monitor agent performance using our observability tools, helping to identify and fix issues like hallucinations or failed API calls. - Build & Test Agents: Develop specific domain agents (e.g., "HR Policy Assistant", "IT Ticket Classifier") using our pre-validated Blueprints and Azure AI Foundry. - Learn & Grow: Rapidly upskill on AKS, Databricks, and LangGraph, moving from building simple chatbots to complex autonomous systems under the mentorship of senior team members. Qualifications: - Foundational Skills: Strong grasp of Python programming. You know your way around data structures, APIs (REST), and basic version control (GitHub). - AI Curiosity: You have experimented with LLMs (OpenAI API, Hugging Face) and understand the basics of Prompt Engineering and RAG. - Tech Savvy: Familiarity with Docker and basic cloud concepts (Azure/AWS) is a big plus. - Mindset: You are a fast learner who isn't afraid to break things in a sandbox to understand how they work. You are passionate about how AI can solve real-world problems. - Team Player: You communicate clearly and are eager to collaborate in an agile, international team environment.