Job
Description
About ZenDot ZenDot is a cutting-edge technology company building AI-driven solutions that power the next generation of productivity, intelligence, and automation for businesses. Our focus lies in delivering enterprise-grade tools that combine large language models, real-time data, and deep integrations across knowledge ecosystems. We're building a state-of-the-art internal platform for enterprise semantic search, secure document retrieval, and intelligent knowledge graphs . To lead this mission, we are hiring a Senior AI Engineer to architect and implement a search and knowledge engine inspired by world-class products like Glean — but tailored to our own innovation roadmap. Key Responsibilities Lead the end-to-end design and implementation of an enterprise semantic search engine with hybrid retrieval capabilities. Build robust, scalable data ingestion pipelines to index content from sources like Google Workspace, Slack, Jira, Confluence, GitHub, Notion, and more. Design and optimize a reranking and LLM augmentation layer to improve the quality and relevance of search results. Construct an internal knowledge graph mapping users, documents, metadata, and relationships to personalize responses. Implement permission-aware access filters , ensuring secure and role-based query results across users and teams. Collaborate on a modular AI orchestration layer , integrating search, chat, summarization, and task triggers. Maintain model benchmarks, A/B testing frameworks, and feedback loops for continuous learning and improvement. Work closely with product, security, infra, and frontend teams to deliver high-performance and compliant AI solutions . Require Skills & Experience 3+ years of experience in AI/ML engineering with deep expertise in information retrieval (IR) , NLP , and vector search . Strong understanding and hands-on work with BM25, vector stores (Faiss, Weaviate, Vespa, Elasticsearch) . Proficiency in transformer-based models (BERT, RoBERTa, OpenAI embeddings) and document embedding techniques . Experience in building hybrid search pipelines (sparse + dense), rerankers, and multi-modal retrieval systems. Skilled in Python , PyTorch/TensorFlow , and data engineering frameworks (Airflow, Spark, etc.). Familiar with RBAC systems, OAuth2 , and enterprise permissioning logic. Hands-on with graph data structures or knowledge graph tools like Neo4j, RDF, or custom DAG engines. Cloud-native architecture experience (AWS/GCP), Kubernetes, and microservices best practices. Bonus Points For Building or contributing to open-source IR/NLP/search frameworks (e.g., Haystack, Milvus, LangChain). Past work with LLM-driven RAG (Retrieval-Augmented Generation) systems. Familiarity with document-level compliance, access auditing, and SAML/SCIM integrations. Ability to work in fast-paced, zero-to-one product environments with deep ownership. Show more Show less
