Lead Data Scientist - AI Knowledge Retrieval Systems

About the Role

We are a fast-growing defense technology company whose AI-powered intelligence platform is deployed across the full spectrum of defense acquisition. We are seeking a Lead Data Scientist to join our team and take charge of the architecture and delivery of our next-generation agentic knowledge retrieval and deep research systems. This Lead Data Scientist remote position is a senior individual-contributor leadership role where you will be the primary technical authority on search science, RAG, knowledge graphs, and multi-agent AI.

What You'll Do

• Architect and lead the delivery of a complex, multi-modal intelligent agent system for knowledge retrieval and deep research, serving as the central nervous system of our AI platform.
• Define the multi-year technical roadmap for AI knowledge retrieval initiatives, translating vague business challenges into concrete, scalable research and product goals.
• Design and deploy agentic AI systems capable of deep conversational knowledge exploration, robust problem solving, and accurate question answering over large, heterogeneous proprietary datasets.
• Lead the development of hybrid knowledge retrieval systems combining embedding models, knowledge graphs, and traditional methods (e.g., BM25) using paradigms such as GraphRAG and RAG-RL.
• Drive state-of-the-art ranking and reranking pipelines — bi-encoder, cross-encoder, multi-tower architectures — within production search and retrieval systems.
• Build and deploy multi-agent AI reasoning frameworks (ReAct, Chain-of-Thought) for complex knowledge exploration and decision support.
• Collaborate with product, data engineering, and software development teams to translate high-level requirements into production-ready AI solutions integrated with client data platforms.
• Mentor and elevate junior and senior engineers, fostering a culture of technical excellence, continuous learning, and high-impact delivery.

Requirements

• 7+ years of professional experience as a Data Scientist in an industry setting.
• Expert-level knowledge of Retrieval-Augmented Generation (RAG) architectures and complex indexing strategies for large-scale, heterogeneous datasets.
• Proven ability to build production-ready knowledge retrieval, conversational AI search, and deep research systems leveraging state-of-the-art LLMs, multi-modal embedding models, vector databases, and knowledge graph systems.
• Deep hands-on experience with hybrid retrieval combining embedding models, knowledge graphs, and traditional methods; practical knowledge of GraphRAG, RAG-RL, and related advanced retrieval paradigms.
• Strong proficiency building and deploying multi-agent AI systems and reasoning frameworks for complex knowledge exploration.
• Excellent communication skills: able to translate complex AI concepts for both technical and non-technical audiences.

Nice to Have

• Experience using AI coding tools (e.g., Claude Code or similar) to accelerate team deliveries at scale.
• Proven track record owning end-to-end execution of large-scale AI/ML projects from ideation to production.

What We Offer

• Base salary around $200,000 based on experience.
• 20-30% bonus paid quarterly.
• Equity between $125,000 - $175,000 with 4 year vesting.
• Unlimited PTO.
• 401(k) with 4% immediate vesting.
• Professional development reimbursement.
• Relocation assistance if needed to move to the Pittsburgh or D.C. area.

This Lead Data Scientist remote role offers the rare combination of cutting-edge AI research, real-world national security impact, and the autonomy to define and build systems that matter. You’ll work on hard problems with exceptional colleagues, on a platform that is genuinely changing how the defense acquisition community operates.