Drata is a leading company in compliance software innovation, dedicated to building trust and security across the internet. They are looking for a Staff Applied AI Engineer to enhance the quality and effectiveness of their AI systems through research, experimentation, and evaluation, focusing on compliance automation.
Responsibilities:
- Design and evaluate information access + reasoning strategies across RAG, agents, and classic ML: chunking, embedding models, hybrid search, metadata filtering, structured retrieval, tool use, and multi-step workflows
- Prototype GenAI workflows (including agentic systems) that map and reason over compliance objects (controls ↔ risks ↔ requirements)
- Explore ML + probabilistic approaches where GenAI is not the best fit: classifiers, ranking models, graph/link prediction, calibration, and weak supervision
- Build and maintain evaluation frameworks: golden datasets, automated quality metrics, regression detection
- Implement and tune ranking/reranking systems: cross-encoders, LLM-based rerankers, learning-to-rank, custom scoring functions
- Run experiments to validate hypotheses and quantify improvements before production rollout
- Debug failure modes and build error taxonomies across retrieval, reasoning, and generation
- Collaborate with AI and Software Engineers to hand off validated approaches for productionization
- Stay current on applied research in RAG, agents, LLM evaluation, and relevance modeling; bring innovations into the product
Requirements:
- 10+ years of experience in applied research, data science, or ML with a focus on NLP, information retrieval, or knowledge systems
- 2+ years of hands-on experience building or contributing to production AI/ML systems
- Strong foundation in information retrieval: dense and sparse retrieval, embedding models, search relevance
- Experience with RAG systems: chunking strategies, vector databases, retrieval optimization
- Proficiency in evaluation methodology: metrics design, golden dataset creation, A/B testing, statistical analysis
- Strong Python skills and comfort with notebook-driven research workflows
- Experience communicating research findings to engineering teams and translating insights into actionable recommendations
- Experience with compliance, legal, or document-heavy domains
- Publications or contributions in IR, NLP, or RAG evaluation