Job
Description
Role Overview: You will lead AI/ML projects focusing on LLMs, fine-tuning, retrieval-augmented generation (RAG), agentic systems, and embedding models. Your responsibilities will include guiding the design and development of scalable Python-based AI systems using frameworks like LangChain, LangGraph, and Hugging Face. You will also develop and integrate advanced chatbot systems (text and voice) with tools such as OpenAI, Claude, Gemini, and vLLM. As part of your role, you will architect and implement solutions using Model Context Protocol (MCP) for managing structured prompt flows, context switching, and modular multi-step agent reasoning. Collaborating with cross-functional teams, including product, data, IT, and support teams, to translate business needs into AI solutions will be essential. Additionally, you will ensure proper orchestration and error handling in agentic workflows and decision automation systems. Contributing to RCD by evaluating emerging AI frameworks and building production-grade reusable components will also be a key responsibility. Effective communication with stakeholders, managing expectations, and providing technical direction throughout the project lifecycle will be crucial. Overseeing code quality, model performance, and deployment pipelines across cloud platforms like AWS is also part of the role. Managing vector search pipelines, data storage solutions (e.g., Neo4j, Postgres, Pinecone), and model inference optimization will be required. Furthermore, you will mentor and guide junior team members in development, best practices, and research. Key Responsibilities: - Lead AI/ML projects involving LLMs, fine-tuning, retrieval-augmented generation (RAG), agentic systems, and embedding models - Guide the design and development of scalable Python-based AI systems using frameworks like LangChain, LangGraph, and Hugging Face - Develop and integrate advanced chatbot systems (text and voice) using tools such as OpenAI, Claude, Gemini, and vLLM - Architect and implement solutions using Model Context Protocol (MCP) for managing structured prompt flows, context switching, and modular multi-step agent reasoning - Collaborate closely with cross-functional teams to translate business needs into AI solutions - Ensure proper orchestration and error handling in agentic workflows and decision automation systems - Contribute to RCD by evaluating emerging AI frameworks and building production-grade reusable components - Communicate effectively with stakeholders, manage expectations, and provide technical direction throughout the project lifecycle - Oversee code quality, model performance, and deployment pipelines across cloud platforms like AWS - Manage vector search pipelines, data storage solutions (e.g., Neo4j, Postgres, Pinecone), and model inference optimization - Mentor and guide junior team members in development, best practices, and research Qualifications Required: - Strong expertise in Python, PyTorch, TensorFlow, LangChain, LangGraph - Familiarity with LLMs (OpenAI, Claude, LLama3, Gemini), RAG, PeFT, LoRA - Knowledge of agentic workflows, prompt engineering, distributed model training - Experience with Model Context Protocol (MCP) for designing modular, reusable prompt frameworks and managing dynamic reasoning contexts - Proficiency in vector databases (Pinecone, Redis), graph databases (Neo4j) - Familiarity with MLOps tools like MLFlow, HuggingFace, gRPC, Kafka - Proven experience deploying models and applications in cloud environments (AWS) - Exceptional communication and stakeholder management skills - Demonstrated ability to lead small teams, manage priorities, and deliver under tight timelines,
