Senior AI Data Engineer

About the role

Coforge is hiring a Senior AI Data Engineer to work remotely on a platform for entity management and governance. The role covers entity types, attributes, cross-references and relationships, and builds and improves Named Entity Recognition (NER) pipelines that combine LLM-based models, gazetteers, pattern matching and blacklists. It also extends NER to new content types such as live-stream content, and improves search and entity discovery.

Key responsibilities

• Evolve and enhance the core platform for entity management and governance, including entity types, attributes, cross-references and relationships.
• Build and improve NER pipelines for text and files, and extend them to new content types.
• Improve search and entity discovery through entity resolution, personalized search, filtering and relationship navigation.
• Design and query graph-based relationship models for traversal, visualization and connected business context.
• Implement entity-level security and access controls across data retrieval and exploration.
• Onboard new data sources and support integrations with consuming applications.
• Translate business requirements into technical solutions and AI workflows, validating AI-generated code and designs.
• Collaborate with stakeholders to shape and prioritize the platform roadmap, and support team onboarding and knowledge sharing.

Required profile

• 7+ years of software engineering experience, including building or managing data-intensive platforms in production.
• Strong systems thinking, architecture and data modeling skills, with experience modeling complex business domains.
• Ability to critically evaluate, validate and correct AI-generated outputs using sound engineering judgment.
• Excellent communication skills.

Required skills

• Elasticsearch or OpenSearch, information retrieval and entity resolution.
• Graph databases and knowledge graphs such as Neo4j and Cypher.
• NLP and NER, including LLM-based extraction and open-source models such as Gemma, Llama, GLiNER or spaCy.
• PostgreSQL, Kubernetes and observability tools such as Datadog.
• Data ingestion and synchronization from multiple source systems.
• AI-assisted development tools such as GitHub Copilot, Cursor, Claude and ChatGPT.
• Knowledge of permission-aware data access and security filtering; proficiency in at least one programming language such as Python or Java.