Description

Lead the design, development, and production deployment of end-to-end Generative AI solutions, including RAG pipelines and AI agents.

This role is on-site.

Responsibilities

• Architect and implement GenAI systems, integrating vector databases and knowledge graphs to ground AI responses and mitigate hallucinations.
• Design, develop, and maintain large-scale knowledge graphs using Neo4j to structure complex enterprise data.
• Build GraphRAG pipelines and scalable data pipelines for ingestion, embedding generation, and continuous model training.
• Collaborate with data scientists to prepare infrastructure for fine-tuning and optimizing Large Language Models (LLMs).
• Provide technical guidance to junior developers and advocate for best practices in CI/CD, testing, and responsible AI.

Required Skills

• 7+ years of experience in software development or AI engineering with production-ready AI projects.
• Expert-level proficiency in Python and frameworks such as PyTorch, TensorFlow, LangChain, and LlamaIndex.
• Strong hands-on experience with Neo4j, including data modeling, Cypher query language, and graph algorithms.
• Deep understanding of GenAI concepts, LLMs, prompt engineering, embeddings, and RAG system architecture.
• Experience deploying and optimizing models in cloud environments, specifically GCP.
• Bachelor's or master’s degree in Computer Science, Data Science, Engineering, or a related technical field.

Preferred Skills

• Experience with MLOps practices and tools.
• Background in translating complex business requirements into scalable AI architectures.

Key Skills

Education

Any Graduate