Position Overview
We are seeking an experienced Senior AI/ML Engineer with strong expertise in Natural Language Processing (NLP), Generative AI, document intelligence, embeddings, and vector search. The ideal candidate will have hands-on experience building enterprise AI solutions that ingest and process documents, generate embeddings, store them in MongoDB, and enable intelligent semantic search using MongoDB Vector Search.
The candidate will work closely with Data, AI/ML, Architecture, and Product teams to design scalable AI-powered document search and Retrieval-Augmented Generation (RAG) solutions.
Key Responsibilities
• Design and develop end-to-end AI/ML and NLP solutions for enterprise document processing and search.
• Build pipelines for document ingestion, text extraction, preprocessing, NLP processing, and enrichment.
• Implement intelligent document chunking and metadata extraction strategies.
• Generate and manage vector embeddings for structured and unstructured data.
• Design and implement MongoDB Vector Search for semantic document retrieval.
• Build RAG (Retrieval-Augmented Generation) pipelines using LLMs and vector databases.
• Develop semantic search capabilities for PDF, Word, text, and other enterprise documents.
• Implement hybrid search combining keyword, metadata, and vector-based retrieval.
• Integrate LLMs and embedding models with enterprise applications and APIs.
• Develop NLP capabilities including NER, classification, summarization, information extraction, and semantic similarity.
• Build scalable Python-based AI/ML services and REST APIs.
• Evaluate retrieval quality using metrics such as Precision@K, Recall@K, MRR, and relevance scoring.
• Optimize chunk size, embedding models, similarity thresholds, and retrieval strategies.
• Implement appropriate security, access controls, monitoring, and governance for enterprise AI solutions.
• Collaborate with architects and engineering teams to productionize AI/ML workloads.
Required Skills
• 8–10+ years of software engineering, data engineering, AI/ML, or related experience.
• Strong hands-on experience with Python.
• Strong experience with Machine Learning and Natural Language Processing (NLP).
• Experience processing unstructured documents and text data.
• Hands-on experience with MongoDB and MongoDB Vector Search / semantic search.
• Experience creating and managing vector embeddings.
• Strong understanding of LLMs, Generative AI, and RAG architectures.
• Knowledge of document chunking, tokenization, similarity search, and retrieval techniques.
• Experience with embedding models from OpenAI, Hugging Face, Sentence Transformers, or equivalent.
• Experience with frameworks such as LangChain, LangGraph, or LlamaIndex.
• Experience building APIs using FastAPI, Flask, or similar frameworks.
• Understanding of prompt engineering, context management, hallucination reduction, and grounding techniques.
• Experience deploying AI/ML applications in cloud environments.
• Strong understanding of production AI considerations including scalability, latency, security, observability, and model evaluation.
Preferred Skills
• Experience with Agentic AI and AI agents.
• Experience with MCP (Model Context Protocol) and enterprise tool integration.
• Knowledge of Azure AI Foundry, Microsoft Fabric, and Databricks.
• Experience with other vector technologies such as FAISS, Pinecone, Weaviate, or Elasticsearch/OpenSearch.
• Experience implementing document intelligence solutions in highly regulated environments.
• Banking or financial-services domain experience is strongly preferred.
Target Architecture
Documents → Text Extraction → NLP Processing → Chunking → Embeddings → MongoDB → Vector Search → RAG/LLM → User Response
The successful candidate should be capable of designing, implementing, optimizing, and productionizing this complete workflow for enterprise-scale document search and AI applications.
