Description

You will architect and deploy end-to-end Generative AI solutions, focusing on RAG pipelines and AI agents. Your work will ground AI responses in factual data using graph databases and vector stores.

Responsibilities

• Design and implement production-ready GenAI systems, including RAG pipelines and autonomous agents.
• Develop large-scale knowledge graphs in Neo4j to structure complex enterprise data.
• Build GraphRAG pipelines that integrate vector databases and knowledge graphs to reduce hallucinations.
• Set up scalable data pipelines for ingestion, embedding generation, and continuous model retraining.
• Collaborate with data scientists to optimize LLM performance and infrastructure on GCP.

Required Skills

• 7+ years of software development or AI engineering experience.
• Expert-level Python proficiency with PyTorch, TensorFlow, LangChain, and LlamaIndex.
• Strong hands-on experience with Neo4j, including Cypher and graph algorithms.
• Deep understanding of LLMs, prompt engineering, and embeddings.
• Experience deploying and optimizing models in Google Cloud Platform (GCP).
• Proven track record of shipping production-ready AI projects.
• Bachelor’s or Master’s degree in Computer Science, Data Science, Engineering, or related field.

Preferred Skills

• Experience with MLOps, CI/CD for AI systems, and responsible AI practices.
• Ability to translate complex business requirements into scalable technical architectures.

Key Skills

Education

Any Graduate