Skip to content
DrataDrataSan Francisco, CA

Platform Engineer, AI Tooling

Platform Engineer building internal AI tooling and agentic workflows to boost engineering productivity at Drata. Focuses on MCP servers, custom AI agents, CI/CD integration, observability, and developer tooling using TypeScript/Python.

Salary not listed
Hybrid3+ YOEDevOps / SRE

About the role

What you'll do

  • Implement custom agent skills, subagents, hooks, and plugins for specific engineering workflows (PR review, test generation, on-call summaries, migration scripts, release notes)
  • Build agentic workflows that automate parts of the coding lifecycle: code generation, verification, testing, and delivery - agents that take a ticket and turn it into a tested, reviewable PR
  • Help engineering teams adopt and customize AI coding tools: pair with them on prompts, debug agents that misbehave, ship the skill that solves their actual problem
  • Wire AI into CI/CD: automated PR review, doc generation, test scaffolding, bug triage
  • Build the observability layer: usage telemetry, cost dashboards, audit logs for AI-driven changes
  • Design and run evaluations for agent workflows
  • Maintain engineering harness that the org reuses across teams
  • Investigate and fix issues: misbehaving agents, eval regressions, cost spikes, permission edge cases in MCP servers
  • Participate in design reviews, post-mortems, and on-call for the AI Tooling platform
  • Write reusable, testable, and efficient code
  • Stay current with new AI coding tools and patterns, and bring back what's useful
  • Research and train on technologies you think may be appropriate for current or future projects

What you'll bring

  • 3+ years of experience as a software engineer building production systems and platforms
  • Daily user of AI coding tools with experience customizing them: skills, rules, subagents, MCP servers, hooks, or extensions
  • Working knowledge of MCP (Model Context Protocol) and how to expose internal tools to AI agents safely
  • Working knowledge of the Anthropic API (preferred) or equivalents: tool use, structured outputs, streaming, prompt caching
  • Solid prompt engineering experience for tasks with tools and multi-step agentic workflows, not just chatbot prompts
  • Strong backend skills: TypeScript or Python in production, REST APIs, async work, relational databases
  • Comfort building developer-facing tooling: CLIs, GitHub Apps, integrations
  • Awareness of the security side of AI dev tools: secrets in prompts, code and data egress, prompt injection inside repos, audit trails
  • Experience with CI/CD systems (GitHub Actions or similar)
  • Working knowledge of the Drata core stack, or willingness to ramp fast: NodeJS/TypeScript primary, with Temporal, MySQL, and REST
  • Experience with AWS
  • Familiarity with engineering productivity measurement frameworks (DORA, DX, SPACE) and what they're trying to capture
  • Curious and hands-on, comfortable in a space where best practices are still being written
  • Experience developing real-world web applications
  • Self-directed and able to own complete features
  • Excellent problem-solving and analytical skills
  • Strong written communication: clear PRs, design docs, runbooks
  • Agile development experience

Nice to have

  • Published agent skills or open-source AI dev tool contributions
  • GitHub App development
  • Terraform

Skills

TypeScriptPythonMcp (Model Context Protocol)Claude APIREST APIsCI/CDGitHub ActionsAWSNode.jsTemporalMySQLTerraformGithub Apps

Similar roles

DevOps / SRE jobs
Forus

Software Engineer, Platform & Infrastructure

ForusNew York, NY

Software Engineer owning Forus' compute platform (EKS/Kubernetes), data layer (Postgres, OpenSearch, BigQuery), cloud cost optimization, reliability (SLOs, observability), and IaC primitives in a regulated healthcare environment. Requires production Kubernetes at scale, deep AWS/Terraform expertise, and database migration experience.

Salary not listed
On-site5+ YOEDevOps / SRE
Forus

Software Engineer, Developer Productivity

ForusNew York, NY

Software Engineer owning CI/CD, build systems, and infrastructure for AI coding agents to accelerate the entire engineering organization's velocity at an AI-powered healthcare network company. Requires strong infrastructure instincts, Python/Bash expertise, and experience driving developer productivity and adoption of agentic workflows.

Salary not listed
On-siteDevOps / SRE
Runloop

Site Reliability Engineer

RunloopSan Francisco, CA

Site Reliability Engineer responsible for the reliability, observability, performance, and security of a core AI agent platform including code sandboxes. Requires 5+ years software engineering experience (3+ in SRE/DevOps), strong CS fundamentals, expertise in containers, cloud IaC, monitoring, and distributed systems.

Salary not listed
On-site5+ YOEDevOps / SRE
Applied Intuition

Build & Release Engineer

Applied IntuitionSunnyvale, CA

Build and maintain CI/CD pipelines, own end-to-end software releases and artifact management with Artifactory, and develop the internal Release Management portal as a hands-on software engineer. Requires 3+ years software development experience and strong CI/CD and Git expertise.

118k – 200k/yr
On-site3+ YOEDevOps / SRE
Lyft

Software Engineer, Async Platform

LyftSeattle, WA

Software engineer building and maintaining a highly scalable asynchronous platform at Lyft. Design, develop and operate tooling for reliability, scalability and efficiency of distributed systems and infrastructure. Requires 5+ years in software development, automation and systems engineering with experience in Go/Python and cloud platforms.

118k – 147k/yr
Hybrid5+ YOEDevOps / SRE