Data Scientist, Software Developer

📋 Description

• Design, develop, and implement AI-driven services for the Compendia Data Platform (CDP), which includes LLM-based NLP functionalities and interoperable (agentic) components.

• Create and sustain evaluation frameworks for LLM - ontology/knowledge base integration, which encompass quantitative metrics, baselines, error analysis, and reporting to facilitate sound architectural decisions.

• Assist in the management of the ontology lifecycle (modeling, inference, validation, and lifecycle workflows) as the ontology module transitions from MVP to GA.

• Collaborate with product and engineering teams to enhance platform stability, performance, and scalability for CDP v1.8 and subsequent versions.

• Participate in proofs of concept (PoCs), demonstrations, and mission-aligned analytics workflows while honoring LANL delivery commitments.

• Keep abreast of pertinent research and emerging trends in semantic engineering, LLM evaluation, and production AI systems; convert insights into actionable, testable solutions.

• Foster a high-performing team culture by delivering mission-focused analytics and software tools that ensure high customer satisfaction and adhere to strict delivery timelines.

⛳️ Requirements

• 2+ years of robust Python proficiency and experience in delivering production software (APIs/services), including testing and version control.

• 2+ years of experience with NLP and/or contemporary LLM workflows (prompting, retrieval, fine-tuning/adaptation, and/or tool/agent integration) along with an understanding of evaluation factors.

• 2+ years of experience in designing experiments and quantitative evaluations (metrics, baselines, error analysis) and effectively communicating results to both technical and non-technical audiences.

• U.S. Citizenship and the capability to obtain a DOE "Q" or DoD Top Secret clearance.

🏝️ Benefits

• Health insurance

• Flexible work arrangements

• Professional development opportunities