About the role
We are looking for a highly skilled Senior Software Engineer - AI and Platform with strong backend and platform engineering expertise to design, build, and scale AI-driven platform capabilities. The role will focus on document processing, information extraction, knowledge graph generation, distributed data systems, and AI-powered backend platforms. The ideal candidate should have strong experience in Python, distributed systems, Kafka, LLM-based information extraction, graph technologies, API frameworks, and modern data platforms.
Responsibilities:
- Develop and maintain scalable backend and platform services using Python, Django REST, and FastAPI.
- Design and support distributed systems and event-driven pipelines using Kafka.
- Build document processing workflows using Docling document-to-markdown.
- Develop LLM-based and agentic information extraction solutions, including NER, tool use, and evaluations.
- Transform protocol documents into structured ontology graphs.
- Design and maintain RDF generation and graph ingestion pipelines.
- Work extensively with Dgraph and graph-oriented data models.
- Develop and integrate backend services using Node.js and Apollo GraphQL Supergraph.
- Manage and optimise data storage and retrieval using MySQL, Redis, OpenSearch, and S3/MinIO.
- Implement solutions aligned with RDF, USDM, and clinical-data standards.
- Collaborate with cross-functional teams to deliver scalable and reliable platform capabilities.
- Contribute to architecture discussions and produce high-quality technical documentation.
Requirements:
- 8-10 years of relevant software engineering experience with a strong focus on backend and platform development.
- Proven experience building scalable, production-grade distributed systems.
- Strong expertise in Python and modern backend frameworks.
- Hands-on experience with AI/LLM-driven platforms and information extraction.
- Exposure to knowledge graphs, RDF, ontology engineering, and graph databases.
- Strong problem-solving and analytical skills.
- Excellent communication and stakeholder management capabilities.
- Ability to work effectively in a fast-paced, collaborative environment.
Required Skills:
- Python
- Distributed Systems
- Kafka / Event-Driven Architecture
- Django REST
- FastAPI
- LLM / GenAI / Agentic AI
- NER, Tool Use and LLM Evaluations
- Document Processing / Docling
- RDF and Graph Data
- Knowledge Graph / Ontology Graph
- Dgraph
- Node.js
- Apollo GraphQL Supergraph
- MySQL
- Redis
- OpenSearch
- S3 / MinIO
- USDM / Clinical Data Standards
- Strong written and verbal communication skills
Nice-to-Have Skills:
- Ontology engineering and knowledge modelling.
- Normalisation and mapping of extracted elements to ontologies.
- Angular 19 / Nx.
- Clinical trials/healthcare / regulated-data domain experience.