Walk-in || Senior Generative AI Engineer - RAG, Lang Graph & Multimodal AI

Role & responsibilities

• Design, develop, and maintain end-to-end Generative AI and Retrieval-Augmented Generation (RAG) solutions for contract document analysis.
• Build scalable document processing pipelines for parsing, chunking, embedding, retrieval, and response generation.
• Develop agentic AI workflows using Lang Graph, Agentic X, or similar orchestration frameworks.
• Implement multimodal AI capabilities to process text, images, tables, and complex document layouts.
• Integrate and fine-tune open-source LLMs such as Llama, Mistral, and Ollama-based models.
• Design and optimize vector search solutions using FAISS, Milvus, Qdrant, or similar vector databases.
• Work with OCR and document parsing frameworks such as Unstructured, Py MuPDF, and PDF Plumber to extract structured insights from contracts.
• Optimize retrieval accuracy, prompt engineering, and response quality for large-scale enterprise applications.
• Work with OCR and document parsing frameworks such as Unstructured, Py MuPDF, and PDF Plumber to extract structured insights from contracts.
• Collaborate with product, data science, and engineering teams to deliver AI-powered document intelligence solutions.
• Ensure scalability, performance, security, and maintainability of AI systems in production environments.
• Stay updated with the latest advancements in LLMs, Agentic AI, RAG architectures, and multimodal AI technologies.

Preferred candidate profile

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related field.
• 5+ years of experience in backend development, AI/ML engineering, or enterprise software development.
• At least 1 year of hands-on experience building Generative AI, RAG, LLM, or Agentic AI solutions.
• Strong expertise in Python and AI frameworks such as LangChain, LlamaIndex, Haystack, and LangGraph.
• Proven experience designing and deploying Retrieval-Augmented Generation (RAG) applications in production environments.
• Hands-on experience with vector databases such as FAISS, Qdrant, Milvus, Pinecone, or Weaviate.
• Experience working with open-source LLMs, including Llama, Mistral, and Ollama-based deployments.
• Strong understanding of document intelligence, PDF parsing, OCR, chunking strategies, embeddings, and semantic search.
• Experience developing scalable APIs and microservices using FastAPI and integrating AI services into enterprise applications.
• Familiarity with multimodal AI models capable of processing text, images, tables, and complex document layouts.
• Knowledge of cloud platforms such as Azure, AWS, or GCP and containerized deployments using Docker and Kubernetes.
• Understanding of prompt engineering, model evaluation, fine-tuning, and optimization techniques.
• Experience in legal technology, contract lifecycle management, compliance automation, or document analytics will be an advantage.
• Strong analytical, problem-solving, and communication skills with the ability to collaborate in cross-functional teams.
• Self-motivated professional who can work independently and deliver high-quality AI solutions in a fast-paced environment.