AI Engineer – RAG & Graph Systems

Experience

• Total Experience: 6-8 years

Required Skill Sets

• We are seeking a highly skilled AI Developer with expertise in Retrieval-Augmented Generation (RAG) models, Knowledge Graphs, and Neo4j to design and implement intelligent systems that enhance data-driven decision-making.
• In this role, you will bridge machine learning, graph databases, and semantic technologies to build scalable solutions for complex information retrieval and reasoning tasks.
• Design, develop, and optimize RAG-based systems to integrate retrieval mechanisms (e.g., vector databases) with generative AI models (e.g., LLMs) for accurate, context-aware responses.
• Architect and maintain Knowledge Graphs to model relationships between entities, enabling semantic search, recommendation engines, and data interoperability.
• Implement graph database solutions using Neo4j, including schema design, Cypher queries, and performance tuning for large-scale datasets.
• Collaborate with data scientists, engineers, and product teams to translate business requirements into technical solutions.
• Evaluate and integrate emerging technologies (e.g., graph neural networks, hybrid search) to improve system capabilities.
• Ensure data quality, security, and compliance in Ai graph-based applications.

Qualifications

• 3 years of experience in AIML development, with 1 year focused on RAG, Knowledge Graphs, or Neo4j. Proficiency in Python and libraries like PyTorch, Hugging Face, or LangChain for RAG implementation.
• Hands-on experience with Neo4j (Cypher, APOC, graph algorithms) and other graph databases (e.g., Amazon Neptune).
• Strong understanding of NLP, semantic technologies (RDF, OWL), and vector search tools (e.g., Pinecone, FAISS).
• Familiarity with cloud platforms (AWS GCP Azure) and containerization (Docker, Kubernetes).
• Problem-solving mindset with the ability to optimize complex systems for scalability and latency.
• Preferred Qualifications Experience with ontology development or linked data standards.
• Contributions to open-source projects in graph AI or RAG.
• Knowledge of DevOps MLOps practices for AI deployment.