Module Lead

Role Overview

We are seeking a highly skilled Senior Software Engineer – AI & Platform to design, build, and scale AI-driven platform capabilities focused on document processing, information extraction, knowledge graph generation, and distributed data systems. The ideal candidate will have strong expertise in backend engineering, distributed architectures, LLM-based data extraction, graph technologies, and modern API frameworks.

Key Responsibilities

• Develop and maintain scalable platform services using Python, Django REST, and FastAPI.
• Build and support distributed systems and event-driven pipelines leveraging Kafka.
• Design and implement document processing workflows using Docling document-to-markdown.
• Develop LLM-based / agentic information extraction solutions including NER, tool use, and evals to transform protocol documents into structured ontology graphs.
• Create and manage RDF generation pipelines and support graph ingestion processes.
• Work extensively with Dgraph graph database and graph-oriented data models.
• Build and integrate backend services using Node.js and Apollo GraphQL supergraph.
• Manage and optimize data storage and retrieval using MySQL, Redis, OpenSearch, and S3/MinIO.
• Implement solutions aligned with RDF and USDM / clinical-data standards.
• Collaborate with cross-functional teams to deliver scalable and reliable platform capabilities.
• Produce high-quality technical documentation and contribute to architecture discussions.

Required Skills

Proficiency in Python, Distributed-systems fundamentals, Kafka / event-driven pipelines, Document processing (Docling document-to-markdown), LLM-based / agentic information extraction (NER, tool use, evals) that turns protocol documents into a structured ontology graph, RDF generation and graph load, Dgraph graph database, Django REST + FastAPI, Node.js, Apollo GraphQL supergraph, MySQL, Redis, OpenSearch, S3/MinIO, RDF and USDM / clinical-data standards. Strong written English is required.

Nice-to-Have Skills

• Ontology engineering / knowledge modelling, including normalizing and mapping extracted elements onto an ontology
• Angular 19 / Nx
• Clinical-trials / healthcare / regulated-data domain experience