Overview: We’re building a production-grade platform to process and analyze large volumes of documents. You’ll work on backend services that handle document ingestion, OCR, AI-based enrichment, and semantic search. This is a real-world system intended for enterprise use, not a research prototype. Key Responsibilities: Design and implement scalable backend services for document ingestion and AI processing. Develop robust REST/JSON APIs with proper validation. Build pipelines for OCR, parsing, metadata extraction, and AI enrichment. Integrate vector search or semantic retrieval functionality. Optimize for performance, reliability, and maintainability. Collaborate on deployment and runtime considerations (Docker, containerized services). Requirements: Strong Python backend experience (FastAPI or similar) Microservices and API-first design experience Document processing (PDFs, OCR, images) AI/ML integration (LLMs, embeddings, classification/extraction) Experience with search/retrieval systems (Elasticsearch, OpenSearch, vector DBs) Knowledge of data modeling and schema evolution Comfortable with Docker/containerized deployments Independent, accountable, and clear communication Preferred: Cloud-native architectures (AWS, Azure, GCP) Event-driven or workflow systems Enterprise security and access control Legal, compliance, or regulated data experience Why Join Us: Work on a high-impact AI platform that’s production-ready and enterprise-grade, collaborating with a technical lead in a disciplined engineering environment.