Job Description
RAG System Development
- Design, implement, and optimize end-to-end RAG pipelines, covering data ingestion, indexing, retrieval, reranking, and response generation.
- Integrate, configure, and tune vector databases such as Pinecone, Weaviate, Milvus, or Chroma.
- Improve chunking strategies, embedding quality, and similarity search effectiveness.
- Build evaluation frameworks to measure RAG performance, including precision, recall, context relevance, and answer quality.
Agentic AI & Intelligent Systems
- Develop AI Agents using frameworks such as LangGraph, AutoGen, or LlamaIndex Agents.
- Design and orchestrate multi-agent workflows (e.g., planner, executor, evaluator).
- Implement tool and function calling, serverless integrations, and adaptive reasoning workflows.
Model Context Protocol (MCP)
- Design and implement MCP servers that expose tools, APIs, and datasets to LLMs.
- Integrate MCP across application layers, from frontend and backend services to LLM components.
- Build custom MCP tools, including database connectors, internal API integrations, and data collection utilities.
System Architecture & MLOps
- Build and maintain model inference infrastructure using Docker, Kubernetes, and GPU-based environments.
- Implement logging, monitoring, and observability for RAG and agent-based pipelines.
- Optimize inference performance and cost through techniques such as batching, quantization, vLLM, and TensorRT.
Requirements
- 3 5+ years of experience in advanced analytics, machine learning, deep learning, or applying AI/GenAI solutions to real-world business problems.
- Strong proficiency in Python (FastAPI or Flask); experience with Node.js is an advantage.
- Proven experience building production-grade RAG systems.
- Deep understanding of LLMs, embeddings, vector databases, and reranking techniques.
- Hands-on experience with RAG and agent frameworks such as LangChain, LlamaIndex, LangGraph, or equivalent.
- Practical knowledge of Docker, Linux, and foundational DevOps practices.
- Strong debugging, problem-solving, and system-level thinking skills.
- Excellent communication and presentation skills, with the ability to clearly explain AI, LLM, and RAG concepts to both technical and non-technical audiences.
- Ability to deliver AI solution demos and presentations, clearly articulating system architecture, workflows, and business value.
- Fluent spoken and written English.
Preferred
- Experience in client training, presales support, solution presentations, or developing AI educational materials (slides, documentation, demos).
- A teaching and mentoring mindset, with the ability to guide junior engineers and support cross-functional teams such as Product, Business, Sales, and Clients in adopting AI solutions.
