Senior AI and Large Language Model (LLM) Engineer

Key Responsibilities

• Serve as the AI/LLM subject matter expert across product and engineering teams.
• Collaborate with product managers and technical leads to define AI-enabled capabilities and define the use of LLMs across NCBI platforms (e.g., PubMed and related systems).
• Develop and implement retrieval-augmented generation (RAG) systems integrating LLMs with large-scale biomedical datasets.
• Provide architectural guidance on model selection, domain adaptation, evaluation strategies, and deployment approaches.
• Improve model grounding, factual accuracy, and scientific reliability in domain-sensitive applications.
• Support engineering teams in productionizing AI solutions, ensuring scalability, performance, and maintainability.
• Evaluate emerging LLM techniques and recommend practical adoption strategies aligned with organizational priorities.

Required Qualifications

• 3+ years of hands-on experience working with large language models (training, fine-tuning, augmentation, or deployment).
• Demonstrated experience integrating LLMs into production systems (e.g., semantic search, RAG pipelines, domain-specific QA).
• Strong experience in ML system architecture and scalable deployment.
• Proven ability to work cross-functionally with product and technical teams.
• Experience serving as a technical SME guiding multi-team initiatives.
• Strong programming skills in Python.
• Experience with modern ML frameworks (e.g., PyTorch, Hugging Face) and retrieval infrastructure (e.g., embeddings, vector databases).

Preferred Qualifications

• Experience building LLM-based systems for biomedical research or life sciences.
• Familiarity with large scientific corpora, biomedical ontologies, structured knowledge bases, or biological datasets.
• Experience developing generative AI systems for DNA, RNA, or protein sequence analysis.
• Background in bioinformatics, computational biology, or related disciplines.
• Experience improving factual grounding and reducing hallucinations in scientific or regulated environments.