We are looking for a highly experienced Generative AI Engineer to join our AI/ML team. The ideal candidate will have a strong background in designing and deploying advanced Retrieval-Augmented Generation (RAG) and Graph-RAG systems in production. This is a critical role focused on building scalable and intelligent AI solutions using state-of-the-art LLMs, agent frameworks, and MLOps tools.
Design, develop, and deploy RAG and Graph-RAG systems at scale.
Integrate and optimize vector and graph databases for efficient information retrieval.
Work with Large Language Models (LLMs), embedding models, and retrieval pipelines.
Leverage MLOps tools to automate and manage AI/ML workflows.
Experiment with and implement Agentic AI systems using frameworks like LangChain Agents, AutoGPT, or CrewAI.
Collaborate with cross-functional teams to deliver robust, production-ready solutions.
Clearly articulate technical decisions, system architecture, and project outcomes to both technical and non-technical stakeholders.
Proven 5+ yrs experience delivering RAG and Graph-RAG solutions in production.
Strong proficiency in Python, vector DBs, and graph DB query languages (Cypher, Gremlin, SPARQL).
Hands-on experience with LLMs, embedding models, and retrieval frameworks.
Familiarity with MLOps tools (MLflow, Airflow, Docker, Kubernetes).
Deep understanding of AI/ML/Data Science principles and practices.
Conceptual knowledge of Agentic AI and autonomous agents (LangChain Agents, AutoGPT, CrewAI).
Ability to clearly articulate past project experience, technical decisions, and outcomes.
RAG, Graph-RAG, Python, vector databases, graph database query languages, Cypher, Gremlin, SPARQL, LLMs, Embedding models, Retrieval frameworks, MLflow, Airflow, Docker, Kubernetes, AI/ML/Data Science principles, Agentic AI, Autonomous agents, LangChain Agents, AutoGPT, CrewAI