Senior AI Platform Engineer — Production ML Infra

Rozgoo; United States; Remote; USD 180,000 - 250,000; Full time

Job summary

Drata's AI Platform team builds the production infrastructure that powers AI features across our compliance platform — from MCP servers that make Drata's data available to AI agents, to LLM workflow orchestration that automates SOC 2, TPRM, and policy analysis.

You'll own the systems that sit between our AI models and our customers: tool definitions that agents actually understand, deployment pipelines that handle model upgrades without breaking output quality, and orchestration layers that

Qualifications

• 7+ years of software engineering experience, with 2+ years building or operating AI/ML infrastructure in production.
• Strong in Python (our AI services are built in Python).

Responsibilities

• MCP Server Development & AI-Optimized API Design: Design and build MCP servers that expose Drata's platform to AI agents and optimize tool schemas for model comprehension.
• Agent Orchestration & Workflow Infrastructure: Build and operate multi-step agent workflows with state management and multi-tenant access.
• LLM Operations & Model Lifecycle Management: Manage model upgrades, prompt versioning, A/B testing, and token capacity planning.
• Production AI Infrastructure & RAG Systems: Oversee vector storage, document pipelines, multi-region deployment, and cost optimization.
• Platform Enablement & Developer Experience: Build CI/CD patterns for AI workflows and provide reliable platform primitives for teams.

Skills

Python

AI/ML infrastructure

Job description

Drata's AI Platform team builds the production infrastructure that powers AI features across our compliance platform — from MCP servers that make Drata's data available to AI agents, to LLM workflow orchestration that automates SOC 2, TPRM, and policy analysis.

You'll own the systems that sit between our AI models and our customers: tool definitions that agents actually understand, deployment pipelines that handle model upgrades without breaking output quality, and orchestration layers that