AI Engineer (Graphs and LLMs)

Qualifications

• Knowledge graph construction, embedding, and reasoning
• Citation networks and bibliographic analysis
• Semantic search and question-answering over medical knowledge bases
• 2+ years of hands-on experience with LLMs and Knowledge Graphs (e.g., Graph-RAG, LLM-based knowledge graph reasoning, or similar architectures)
• Strong foundation in deep learning frameworks (PyTorch)
• Experience with Large Language Models (transformers, fine-tuning, RAG systems)
• Proficiency in Python and modern ML development tools
• Experience putting AI systems into production environments
• Strong understanding of NLP, information retrieval, and knowledge representation
• Ability to read and implement research papers
• Excellent communication skills and ability to work collaboratively

Responsibilities

• Develop Graph-Enhanced LLM Systems: Design and implement state-of-the-art architectures that combine Graph Neural Networks with Large Language Models to reason over complex networks of biomedical knowledge, literature, and clinical evidence
• Build Clinical Knowledge Discovery Tools: Create AI-powered systems that enable physicians to rapidly synthesize insights from scientific literature, clinical trials, guidelines, and emerging research—transforming weeks of literature review into minutes of intelligent querying
• Scientific Knowledge Graph Construction: Build and maintain dynamic knowledge graphs that capture relationships between medical concepts, research findings, clinical guidelines, drug interactions, and treatment protocols from millions of publications
• Science of Science Applications: Apply bibliometric analysis, citation networks, and knowledge evolution modeling to identify emerging research trends, contradictory findings, and knowledge gaps in medical literature
• Multi-Document Reasoning: Develop systems that perform sophisticated reasoning across thousands of research papers, synthesizing evidence, resolving contradictions, and providing confidence-weighted clinical insights
• Production Systems: Deploy robust, scalable AI systems that handle real-time queries over massive biomedical knowledge bases with appropriate attention to accuracy, citation traceability, and clinical safety
• Graph LLM architectures and graph-augmented language models
• Multi-hop reasoning over document graphs
• Retrieval-Augmented Generation (RAG) over scientific literature
• Named Entity Recognition and relation extraction from biomedical text
• Evidence synthesis and contradiction detection

Full Description

What You'll Do

• Develop Graph-Enhanced LLM Systems: Design and implement state-of-the-art architectures that combine Graph Neural Networks with Large Language Models to reason over complex networks of biomedical knowledge, literature, and clinical evidence

• Build Clinical Knowledge Discovery Tools: Create AI-powered systems that enable physicians to rapidly synthesize insights from scientific literature, clinical trials, guidelines, and emerging research—transforming weeks of literature review into minutes of intelligent querying

• Scientific Knowledge Graph Construction: Build and maintain dynamic knowledge graphs that capture relationships between medical concepts, research findings, clinical guidelines, drug interactions, and treatment protocols from millions of publications

• Science of Science Applications: Apply bibliometric analysis, citation networks, and knowledge evolution modeling to identify emerging research trends, contradictory findings, and knowledge gaps in medical literature

• Multi-Document Reasoning: Develop systems that perform sophisticated reasoning across thousands of research papers, synthesizing evidence, resolving contradictions, and providing confidence-weighted clinical insights

• Production Systems: Deploy robust, scalable AI systems that handle real-time queries over massive biomedical knowledge bases with appropriate attention to accuracy, citation traceability, and clinical safety

Technical Focus Areas

• Graph LLM architectures and graph-augmented language models

• Knowledge graph construction, embedding, and reasoning

• Citation networks and bibliographic analysis

• Multi-hop reasoning over document graphs

• Retrieval-Augmented Generation (RAG) over scientific literature

• Named Entity Recognition and relation extraction from biomedical text

• Evidence synthesis and contradiction detection

• Semantic search and question-answering over medical knowledge bases

Qualifications

Required

• Master's degree in Computer Science, Machine Learning, Computational Biology, Information Science, or related quantitative field (PhD preferred)

• 2+ years of hands-on experience with LLMs and Knowledge Graphs (e.g., Graph-RAG, LLM-based knowledge graph reasoning, or similar architectures)

• Strong foundation in deep learning frameworks (PyTorch)

• Experience with Large Language Models (transformers, fine-tuning, RAG systems)

• Proficiency in Python and modern ML development tools

• Experience putting AI systems into production environments

• Strong understanding of NLP, information retrieval, and knowledge representation

• Ability to read and implement research papers

• Excellent communication skills and ability to work collaboratively

Preferred

• Experience with graph databases.

• Demonstrated experience in Science of Science or Knowledge Discovery (bibliometrics, citation analysis, research trend detection, or scholarly knowledge mining).

• Publications in top-tier ML/AI/IR conferences (NeurIPS, ICML, ACL, EMNLP, WWW, KDD, etc.)

• Experience with biomedical literature databases (PubMed, MEDLINE, clinical trial registries)

• Background in biomedical NLP or clinical informatics

• Experience with vector databases and semantic search systems

• Familiarity with clinical decision support tools or medical information retrieval