Job Description

Who we are

What you'll be doing

• Design and implement LLM-powered applications using advanced techniques such as: Retrieval-Augmented Generation (RAG); Multi-agent systems/agent workflows; Context-aware, multi-turn conversational AI
• Build and optimize pipelines using frameworks such as: LangChain, LangGraph, CrewAI
• Ensure secure LLM usage, including: prompt injection mitigation; safe prompt design and validation; data privacy and access control
• Build frameworks using: FastAPI, Flask, or Django
• Design and implement: Microservices architecture, distributed systems, secure API patterns with authentication and authorization
• Integrate APIs (REST / OData) with enterprise systems
• Develop a React-based conversational UI with: Streaming responses (real-time token flow); Chat history and multi-turn conversation management
• Tool usage visualization (agent/tool execution display)
• Build and maintain production-ready ML/AI systems:
• CI/CD pipelines for ML and application code
• Model deployment and monitoring pipelines
• Use tools and platforms such as: Docker, Kubernetes, Azure ML, Databricks, or AWS
• Ensure system scalability, reliability, and observability
• Integrate with enterprise platforms and tools such as: MXP, LeanIX, Gainsight (or similar ecosystems)
• Implement RAG pipelines for: QBR (Quarterly Business Review) insights and reporting
• Handle structured and unstructured data ingestion and transformation
• Implement MCP (Model Context Protocol) client integration in Python
• Enable interaction between LLMs and enterprise tools/services
• Build modular tool ecosystems to support agent-based workflows

What you'll bring along

• BSc/MSc in Computer Science or related field
• Core stack: Python (mandatory), Node.js or Java (nice-to-have but preferred); FastAPI, Flask, or Django
• React (for frontend-focused roles)
• Experience designing and building microservices-based and distributed systems
• Strong understanding of secure API design, authentication, and system integration
• Hands-on experience with REST and/or OData APIs
• Practical experience with LLMs, Retrieval-Augmented Generation (RAG), and agentic AI systems
• Familiarity with frameworks such as LangChain, LangGraph, or CrewAI
• Strong skills in prompt engineering and secure LLM implementation, including mitigation of prompt injection risks
• Experience working with containerization and orchestration tools such as Docker and Kubernetes
• Proven ability to build and maintain CI/CD pipelines
• Hands-on experience with cloud platforms such as Azure ML, Databricks, or AWS