Machine Learning Research Engineer II

This role focuses on building intelligent systems that transform unstructured documents and structured system data into actionable knowledge, connected via an evolving knowledge graph. This position will develop and integrate named entity recognition (NER), topic modeling, correlation algorithms, and a recommendation system to link extracted insights across domains—powering intelligent applications for decision support, analytics, and automation. The day-to-day activities of this position are working within the project team to: Design and implement ML pipelines to extract entities, topics, and relationships from unstructured text (e.g., PDFs, reports) and structured data sources Build scalable ingestion systems for integrating document-based and API-driven data streams into a unified context layer Apply and fine-tune NER, topic modeling, and clustering techniques using modern frameworks (spaCy, HuggingFace, scikit-learn, etc.) Correlate and link extracted data into a graph-based knowledge representation using platforms like Memgraph or Neo4j Develop and deploy recommendation systems to suggest relevant content, actions, or knowledge graph entities based on user profiles, extracted insights, or contextual cues Implement LLM-powered search capabilities that leverage embeddings, vector databases, and semantic understanding for intelligent querying across documents and graph data Integrate ML outputs into full-stack applications built on React, Go, GraphQL, and PostgreSQL Work with LangChain and LLM APIs (OpenAI, vLLM, Ollama) to enrich query capabilities and agent reasoning Collaborate with infrastructure engineers to containerize and automate deployments via Docker and GitLab CI/CD