Senior AI Engineer
Designs, builds, and scales agentic AI systems using LLMs for compliance automation, including multi-step reasoning, RAG, and production deployment. Requires 7+ years software engineering with 2+ years ML/AI, Python proficiency, and cross-functional collaboration.
About the job
Responsibilities
Build Agentic & Intelligent AI Systems
- Design and implement LLM-powered systems capable of multi-step reasoning, evidence grounding, and decision support in high-trust domains.
- 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 alignment, and evidence validation.
- Ensure AI outputs are traceable, explainable, and auditable, meeting the expectations of enterprise customers and auditors.
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 with diverse skill sets 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 trust principles.
Requirements
- 7+ years of hands-on software engineering experience; 2+ years specifically in ML/AI engineering.
- Proficiency in Python; TypeScript experience is a plus, especially for production AI system integrations.
- 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, and evaluation.
- Track record of taking AI systems from concept to production, designing scalable, maintainable solutions.
- 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, engineering teams, and partnering with other application development teams with diverse skill sets.
Nice-to-Haves
- 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.
Skills
Python, TypeScript, LLMs, RAG, Agent Frameworks, Prompt Engineering, Vector Databases, Pinecone, Chroma, Faiss, Embeddings, Snowflake, Knowledge Graphs
Similar jobs
ML Engineering jobs
Mercury
San Francisco, CABuild and operate the platform that deploys, serves, observes, and retrains production machine-learning models for real-time fraud and financial-crime risk decisions. Requires 5+ years of ML engineering, backend, or MLOps experience, strong Python skills, and production model-serving expertise.
Traba
New York, NYBuild and deploy production AI-agent systems, including their harnesses, evaluations, orchestration, and supporting services. The role requires 5+ years of software engineering experience, production LLM or agent experience, and strong Python or TypeScript/Node.js skills.
Front
San Francisco, CA
Build and deploy generative AI and LLM-powered agentic applications at Front to automate customer support inquiries, enhance product capabilities, and drive operational insights. Requires 5+ years software engineering experience with strong production AI/ML focus, agentic/RAG expertise, and proficiency in Node.js, TS, and Python.
Baselayer
San Francisco, CA
Senior AI Engineer responsible for production LLM agents that enrich business identity data through web discovery, verification, classification, and risk scoring. The role requires strong asynchronous Python, agent and evaluation expertise, browser automation, and experience operating AI systems in production.
Blee
San Francisco, CA
Designs and ships production multi-agent compliance systems, including LLM pipelines, model training, evaluation, monitoring, and explainability. Requires 5+ years of applied AI/ML engineering experience, strong Python, and experience deploying production ML systems.