M

Macroscope

AI-powered codebase analytics & bug fixes

Senior Security Engineer

Full-Time
$190k - $300k/yr
Senior
San Francisco, CA, USA
In Person
CybersecuritySecurity Engineering & Architecture

About the job

Requirements
  • Deep experience securing distributed backend systems at scale, including threat modeling and designing pragmatic defenses for real-world production environments.
  • A proven track record of building and scaling products, not just writing policies, and the ability to embed security into architecture, code, and developer workflows.
  • Strong expertise in secure system design for resilient, performant, maintainable services and application programming interfaces, including authentication and authorization, data protection, service-to-service security, and secure defaults.
  • Strong proficiency with cloud environments, ideally Google Cloud Platform, including networking, identity and access management, organization policies, monitoring, and infrastructure as code.
  • Experience leading security or engineering projects and driving architectural decisions in high-growth teams.
  • Hands-on experience with secrets management, key management and cryptography basics, and secure data handling, including encryption in transit and at rest, least privilege, and secure storage patterns.
Responsibilities
  • Design and implement security architecture, controls, and secure-by-default practices across distributed systems, infrastructure, and application programming interfaces.
  • Protect customer data, harden the production environment, and raise the security bar across shipped software.
  • Establish best practices in identity and access management, cloud security, secure continuous integration and continuous delivery, secrets management, vulnerability management, and production monitoring.
  • Work directly with founders, engineers, and the designer to make architectural decisions that shape the product and company.
  • Build secure systems and help the team move quickly without compromising safety.
Desired Qualifications
  • Strong experience with Go, the primary backend language.
  • Use artificial intelligence tools to accelerate engineering work and stay current with developments.
  • Experience securing artificial intelligence and machine learning systems, including large language models and retrieval-augmented generation, protecting private data, preventing prompt and data leakage, and designing guardrails against common attack patterns.
  • Exposure to Temporal as a worker management system.
  • Being a team player who elevates others.

About the company

Macroscope provides an AI-powered software development analytics platform that connects to a company’s GitHub to understand and improve its codebase. It analyzes abstract syntax trees to map code structure and reviews pull requests in real time to detect bugs, explain issues in plain language, and suggest fixes. For managers and non-technical staff, it offers dashboards showing developer time on updates, AI-generated summaries, and data on project contributors, with integrations to Jira, Linear, and Slack. The goal is to give teams a clear, AI-assisted view of how work gets done to speed up bug fixes, improve code quality, and transparently track development progress.

Company Size

11-50

Company Stage

Series A

Total Funding

$40M

Headquarters

San Francisco, California

Founded

2023

Get referred to Macroscope

See people who can refer or advise you

Simplify Jobs

Simplify's Take

What believers are saying

  • Pydantic said Macroscope auto-approves 91% of PRs and quadrupled weekly throughput by September 2026.
  • Macroscope launched Murmur on September 3, 2026, and is onboarding teams in early preview.
  • Usage-based pricing went companywide in April 2026, reducing seat friction for larger engineering orgs.

What critics are saying

  • CodeRabbit, Greptile, and Graphite attack the same GitHub review workflow with broader ecosystems.
  • Murmur remains early preview on September 24, 2026, so reliability failures stall expansion.
  • If GitHub, OpenAI, or Anthropic bundle review agents, Macroscope's standalone product gets commoditized.

What makes Macroscope unique

  • Macroscope uses AST-based codewalkers and reference graphs, not diff-only LLM review.
  • Approvability graduated from beta on September 12, 2026, auto-approving safe PRs.
  • Murmur orchestrates fleets of coding agents across customer VPCs and cloud sandboxes.

Help us improve and share your feedback! Did you find this helpful?

Growth & Insights and Company News

Headcount

6 month growth

-3%

1 year growth

-3%

2 year growth

-3%
Macroscope
Sep 18th, 2026
How Pydantic merges 91% of their pull requests without a human.

How Pydantic merges 91% of their pull requests without a human. Before Macroscope, Pydantic's coding agents were opening PRs faster than its engineers could review them. Today, Macroscope's Approvability approves roughly 91% of Pydantic's PRs, escalating the rest to human reviewers. Why Pydantic chose Macroscope. Pydantic evaluated every code review tool it could find. What set Macroscope apart from the other code review tools Pydantic tried was the specificity of its feedback: it found actionable bugs, pinpointed the problematic lines of code, and explained how to fix them. The team could confidently turn it on across their repositories without needing to tune it for each repo or engineer. Macroscope has transformed the speed at which the Pydantic team ships code. Before Macroscope, Pydantic was averaging 100-150 PRs a week. Now, that number has increased 4X to ~500 PRs a week. Auto-Approving safe PRs. Pydantic adopted Approvability to split their PR queue into two camps: changes that Macroscope deems safe to merge without human review, and changes that warrant human attention. Approvability now approves ~91% of Pydantic's PRs and escalates the rest to human reviewers, so the engineering team can spend their review time on changes that actually require human judgment. Encoding Pydantic's review standards. Getting to a 91% approval rate took more than bug detection. It meant codifying everything a human reviewer would check and automating the conventions Pydantic's engineers had been enforcing by hand. The Pydantic team had agents read a year's worth of human-written PR comments and turned the feedback their senior and principal engineers gave most often into Macroscope Check Run Agents. Pydantic now runs a large suite of Check Run Agents across the codebase, enforcing their review standards across style, security, performance and safety. Keeping product and engineering in sync. Pydantic also uses Macroscope Status to see where engineering effort is going and how that effort connects to their product goals. Bill Easton, Head of Product at Pydantic, described it as especially valuable through his first weeks at the company. Seeing what the team was working on and shipping gave him a picture of the product that would otherwise have taken months of conversations and research to assemble. Shipping a full epic in an afternoon with Murmur. With code review covered, the constraint moved upstream to writing the code. Pydantic became an early customer of Murmur, Macroscope's agent orchestration platform. Each week the Pydantic team plans an epic in GitHub and spawns dozens of Murmur agents against the parallelizable work, each in its own cloud VM running Pydantic's full development stack. The agents verify their changes, open pull requests, and implement Macroscope's review comments until the work is clear to merge. With Murmur, work that used to take the team 15 hours now takes two. Watch the full conversation with Bill Easton, Head of Product at Pydantic, to hear how his team puts it all into practice. Pydantic: The most depended-on library in Python. Pydantic is the type-safety layer most of Python runs on. Founded by Samuel Colvin in 2017, today nearly every Python agent framework is built on Pydantic. Pydantic has 16.9 billion downloads; more than 900,000 GitHub repositories depend on it. Pydantic Validation is the layer underneath the OpenAI SDK, Anthropic SDK, Google ADK, LangChain and LlamaIndex: most Python code that calls a frontier model runs through Pydantic. The company now builds Pydantic Validation, the open-source library that started it; Pydantic AI, a framework for building agents in Python; and Logfire, an observability platform for monitoring agents at scale in production. Nearly every Python agent framework in use today is built on Pydantic. Get $100 in free usage to run Macroscope on real PRs.

Medium
Sep 20th, 2025
Macroscope Secures $40M to Enhance AI Code

Former Twitter executives have launched a startup, Macroscope.com, securing $40M in funding. The project aims to address issues in AI-generated code, such as inconsistent quality and security vulnerabilities. Macroscope.com offers tools to ensure code quality, acting as a "quality inspector" for AI-generated code. The funding will help refine technology, expand the team, and accelerate product rollouts, potentially revolutionizing the AI code space.

SiliconANGLE Media
Sep 17th, 2025
Macroscope raises $30M to speed up software projects with AI

Macroscope previously raised a $10 million seed round that included the participation of Alphabet Inc.'s GV startup fund, Thrive Capital and Adverb.

LSVP
Sep 17th, 2025
Macroscope Secures $30M Series A Funding

Lightspeed is leading a $30M Series A funding round for Macroscope, an AI-powered tool for teams, founded by Kayvon Beykpour, Joe Bernstein, and Rob Bishop. This brings Macroscope's total funding to $40M. The platform uses AI to provide real-time insights into codebases, reducing the need for meetings and JIRA tickets. It traverses the Abstract Syntax Tree to offer comprehensive code understanding and automated bug fixing, outperforming competitors like Code Rabbit and Graphite.