Senior AI Engineer, Agent Harness

What you'll do

Build Agentic & Intelligent AI Systems

• Design and implement LLM-powered systems capable of multi-step reasoning, evidence grounding, and decision support in high-stakes compliance environments
• Develop agentic workflows that combine retrieval, tool use, structured reasoning, and human oversight
• Create interactive AI experiences that allow users to engage naturally with complex compliance and risk data

Automated Reasoning Over Regulations & Evidence

• Build AI systems that reason over structured and unstructured data to support regulatory interpretation, control validation, and risk assessment
• Ensure AI outputs are traceable, explainable, and auditable, meeting the expectations of enterprise compliance teams

Production-Grade AI Architecture

• Architect and deploy scalable LLM + retrieval + agent systems in production environments
• Optimize for latency, cost, reliability, and evaluation in real-world enterprise workloads
• Partner with platform, security, product teams, and other application development teams to operationalize AI safely and effectively

Responsible & Trustworthy AI

• Embed human-in-the-loop workflows, confidence thresholds, and safety guardrails into AI systems
• Ensure privacy-preserving data handling, robust failure modes, and transparent behavior aligned with Drata's values

What you'll bring

Experience

• 5+ years of hands-on software engineering experience
• 2+ years specifically in ML/AI engineering

Technical Skills

• Proficiency in Python; TypeScript experience is a plus, especially for production AI system integration
• Familiarity with vector databases (Pinecone, Chroma, FAISS, etc.) and RAG system design
• Proven experience building and shipping LLM-based applications in production, including embeddings, RAG, agent frameworks, prompt engineering
• Track record of taking AI systems from concept to production, designing scalable, maintainable solutions

Soft Skills

• Ability to decompose complex tasks into agentic workflows and reason over high-stakes, structured, and unstructured data
• Experience working cross-functionally with product, compliance, security, and engineering teams

Bonus Qualifications

• Experience in compliance, security, risk, or audit domains
• Familiarity with Snowflake-based analytics, knowledge graphs, or enterprise data platforms
• Experience partnering with non-technical stakeholders such as compliance or GRC teams

Impact

• Establish foundational agentic AI capabilities that power multiple present and future product experiences
• Enable customers to derive accurate, explainable insights from complex compliance and security data
• Set the technical and ethical standard for applying modern AI in regulated, high-stakes environments

How we support you

• Competitive base salary, benefits, and stock (typically RSUs)
• Up to 100% employer-paid medical, dental, and vision premiums
• 401(k) plan, company-paid life and disability insurance
• Paid parental leave after six months
• Generous annual professional and personal development stipends
• Flexible vacation policy and paid holidays
• Equity participation with RSUs