Key Responsibilities

• Design and develop advanced conversational AI solutions leveraging Large Language Models (LLMs) and RAG architectures.
• Optimize information retrieval pipelines using embeddings, vector search technologies, and reranking models to improve response relevance and accuracy.
• Design and implement autonomous AI agents capable of utilizing external tools and services through Model Context Protocol (MCP) environments.
• Build robust data ingestion and semantic indexing pipelines for complex document types, including structured technical documentation, tables, and multi-column PDFs.
• Implement intelligent chunking and document processing strategies to maximize retrieval effectiveness.
• Containerize and deploy AI services using modern cloud-native technologies, ensuring scalability, reliability, and maintainability.
• Monitor model performance, costs, latency, and output quality through LLMOps practices and observability platforms.
• Analyze prompts, traces, and user feedback to continuously enhance AI system effectiveness and user experience.
• Collaborate closely with technical teams and business stakeholders to deliver innovative AI-driven solutions.

Requirements

• Proven experience with Python and modern web development frameworks such as FastAPI or Flask for building RESTful APIs.
• Strong hands-on experience with LLM orchestration frameworks, including LangChain , LlamaIndex , or direct LLM API integrations.
• Deep understanding of Retrieval-Augmented Generation (RAG) architectures and semantic search systems.
• Experience working with Vector Databases such as Qdrant , Milvus , Pinecone , Weaviate , or pgvector .
• Solid knowledge of Prompt Engineering techniques and AI agent development through function calling and tool integration.
• Experience with containerization using Docker and orchestration with Kubernetes .
• Familiarity with enterprise cloud environments, particularly Google Cloud Platform (GCP) and/or Microsoft Azure .
• Experience managing source control, CI/CD pipelines, and software delivery processes using GitLab .
• Hands-on experience with LLM observability and monitoring platforms, particularly Langfuse , including prompt tracking, latency monitoring, token usage analysis, and user feedback collection.
•