3
points
dangelosaurus
Joined 27 karma
CTO & Co-founder at Promptfoo https://promptfoo.dev
Previous:
- VP Engineering at SmileID https://usesmileid.com
- CTO & Co-founder at Arthena https://arthena.com (YC W17 - Acquired)
- Co-founder at Matroid https://www.matroid.com (2015)
Website: https://mldangelo.com
GitHub: https://github.com/mldangelo
LinkedIn: https://www.linkedin.com/in/michaelldangelo/
- I ran a red team eval on GPT-5.2 within 30 minutes of release:
Baseline safety (direct harmful requests): 96% refusal rate
With jailbreaking: 22% refusal rate
4,229 probes across 43 risk categories. First critical finding in 5 minutes. Categories with highest failure rates: entity impersonation (100%), graphic content (67%), harassment (67%), disinformation (64%).
The safety training works against naive attacks but collapses with adversarial techniques. The gap between "works on benchmarks" and "works against motivated attackers" is still wide.
Methodology and config: https://www.promptfoo.dev/blog/gpt-5.2-trust-safety-assessme...
- I felt obligated to submit a fix: https://github.com/a16z-infra/reading-list/pull/9
Used Claude to fact-check and fix errors that were likely introduced by Cursor.
The circle is complete.
- I did similar measurements back in July (https://www.promptfoo.dev/blog/grok-4-political-bias/, dataset: https://huggingface.co/datasets/promptfoo/political-question...). Anthropic's "even-handedness" asks: does the model engage with both sides fairly? My study asked: where does the model actually land when it takes positions? A model can score 95% on even-handedness (engages both sides well) while still taking center-left positions when pushed to choose. Like a debate coach who trains both teams equally but votes left.
From my 2,500 questions: Claude Opus 4 was most centrist at 0.646 (still left of 0.5 center), Grok 4 at 0.655, GPT-4.1 most left at 0.745.
The bigger issue is that Anthropic's method uses sanitized prompt pairs like "argue for X / argue against X." But real users don't talk like that - they ask loaded questions like "How is X not in jail?" When you test with academic prompts, you miss how models behave with actual users.
We found all major models converge on progressive economics regardless of training approach. Either reality has a left bias, or our training data does. Probably both.
- Promptfoo | Senior/Staff Engineers, Security Researchers, GTM & Founding Operators | REMOTE (North America) / Hybrid San Mateo CA | Full-time | https://promptfoo.dev
Promptfoo is the MIT-licensed open-source toolkit 125 000+ developers use to evaluate and secure LLM apps. We just closed an $18.4 M Series A led by Insight Partners with participation from a16z and are scaling a small, senior team of high-agency builders.
Open roles
- Senior / Staff Full-stack Product Engineer (TypeScript + Python)
- Senior / Staff AI Security & Red-Team Engineer
- Solutions Architect / SE (multiple)
- Product Marketing Manager (cyber focus)
- Enterprise Account Executive (Bay Area, multiple)
- Technical Writer
- Developer Advocate
Why join
- Build the definitive AI security stack already used at 30+ Fortune 500s.
- Work in open source.
- Competitive salary, meaningful equity, async-friendly culture of ownership.
How to apply
1. Skim https://github.com/promptfoo/promptfoo then run:
2. Email careers@promptfoo.dev with subject “HN – July 2025”, a short intro, and a GitHub / LinkedIn link.npx promptfoo@latest init --example getting-started3. I reply to every thoughtful application and send swag to anyone who tries or contributes to Promptfoo.
Careers page: https://www.promptfoo.dev/careers/
- Promptfoo | Senior/Staff Engineers, Former Technical Founders & Experienced Operators | Remote (US time zones) / Hybrid San Mateo CA | Full-time
Promptfoo is the MIT-licensed open-source toolkit 100 k+ developers use to evaluate and secure their LLM apps. We are funded by top investors and operate as a tight, all-senior team of high-agency builders, former founders, and owner-operators.
10+ open roles - Senior Full-stack Product Engineer (TypeScript + Python) - Solutions Engineer / Architect (multiple positions available). - Senior / Staff Applied-ML & LLM Security Engineer - Red-Team Researcher - Developer Advocate / DevRel - COO / Chief of Staff - Product Marketing (Cybersecurity experience preferred) - Account Executives (Cybersecurity sales background preferred, Bay Area Required)
Even if none of these titles fit exactly, reach out — we hire great builders.
How to apply
Careers page (not every role posted): https://www.promptfoo.dev/careers/1. Skim https://github.com/promptfoo/promptfoo and run `npx promptfoo@latest init --example getting-started` 2. Email careers@promptfoo.dev with subject line “HN” and a short, personalized intro (LinkedIn, resume, or GitHub link welcome). 3. I reply to every thoughtful application and will send swag if you try (or contribute to) Promptfoo. – Michael, co-founder/CTO - I founded and ran a YC company for 8 years before joining Smile ID. Smile ID is a fantastic place to work: meaningful mission, challenging engineering problems (scaling ML pipelines, multimodal models, hundreds of real-world enterprise integrations), and a genuinely talented team. You’re helping hundreds of millions of people access critical services—it’s incredibly rewarding. Highly recommend applying if you want tangible impact, great colleagues, and (optionally!) opportunities to travel in Africa.
- Promptfoo | Multiple Roles | Remote US (HQ: San Mateo, CA)
About us:
Promptfoo builds the leading open-source framework for LLM security and evaluation. Our tools help over 50,000 developers test and secure AI applications. Backed by a16z and led by YC alumni, we are shaping the future of AI safety.
Open Roles:
- Staff Engineers
- Research Engineers
- Developer Relations
How to apply:
- Try Promptfoo at <https://promptfoo.dev>
- Review our code at <https://github.com/promptfoo/promptfoo>
- Email careers@promptfoo.dev with "HN" in the subject, your GitHub/LinkedIn, and a brief note on why you're excited about our work.
Join us in building safer, more reliable AI.
- Promptfoo | Multiple Roles | Remote US (HQ: San Mateo, CA)
We’re building the leading open-source framework for LLM security and evaluation, trusted by 40,000+ developers. Backed by a16z and led by YC alumni, we are shaping the future of AI safety and reliability.
Open Roles:
- Staff Engineers
- Research Engineers
- DevRel
We value experience with open-source projects and a strong interest in AI/ML evaluation, safety, and security. Your work will directly shape how the world responsibly builds, tests, and deploys LLMs and LLM-powered applications.
How to Apply:
Try Promptfoo at https://promptfoo.dev and check out our GitHub at https://github.com/promptfoo/promptfoo. Then email your GitHub/LinkedIn and a short intro to careers@promptfoo.dev. Use "HN" in the subject line. Please try promptfoo before applying - strong preference will be given to candidates familiar with our work.
- Promptfoo | Senior/Staff Software Engineer | SF Bay Area or Remote (US) | Full-Time | AI Security & Open-Source
About Us:
Promptfoo is building the leading open-source toolkit for testing and evaluating large language models (LLMs). We are a small, high-impact team backed by Andreessen Horowitz, shaping the future of AI safety. Trusted by over 40,000 developers, we focus on making LLMs safer, more reliable, and robust with tools for red teaming and pentesting AI.
Preferred Qualifications:
- Ability to work independently, ship features quickly, and prioritize effectively.
- Proficiency in Python and TypeScript; experience with LLMs or open-source projects is a plus.
- Strong background in AI/ML with a passion for security engineering.
Check out our GitHub to explore our work. To apply, email careers@promptfoo.dev with “HN” in the subject line, your GitHub/LinkedIn, and a brief note on why Promptfoo excites you. We will respond to every email. Preference will be given to applicants who have tried or contributed to Promptfoo.
- Promptfoo | Applied ML + Founding Sales Role | San Mateo, CA or REMOTE (US) | Full-time | https://promptfoo.dev
Promptfoo builds open-source pentesting and redteaming tools for LLMs. Our tools are used by over 35,000 developers at companies like Shopify, Amazon, and Anthropic, and OpenAI. We are backed by a16z and we’re hiring:
1. Senior / Staff Applied ML Develop redteaming tools, implement research, and secure LLMs. Experience in TypeScript and Python required.
2. Founding Sales Drive revenue, shape strategy, and build enterprise relationships. Experience selling security or dev tools preferred.
Before applying, try promptfoo at https://github.com/promptfoo/promptfoo. Email careers@promptfoo.dev with "HN" in the subject and a brief intro. We will respond to every application.
- Promptfoo | Senior Software Engineer (AI Security) | SF Bay Area or Remote (US) | Full-time | https://promptfoo.dev
Promptfoo is building open-source pentesting tools for LLMs. Backed by a $5.3M seed round led by Andreessen Horowitz, we’re looking for senior engineers passionate about AI security to join our growing team.
We offer a competitive salary and equity, along with a fully remote, async-first culture. This is a chance to shape the future of AI security while working with a talented and motivated team.
Before applying, please take a moment to try out our product at https://promptfoo.dev and read through our code. If you’re excited about what we’re doing, send an email to careers@promptfoo.dev with "HN" in the subject. Include your LinkedIn or GitHub profile and a brief note on why you’re interested in Promptfoo. We’ll give preference to applicants who have tried or contributed to promptfoo.
Join us in building the future of AI security!
- Promptfoo | Software Engineer | SF Bay Area or Remote (US) | Full-time | https://promptfoo.dev
Promptfoo recently raised $5M in a seed round led by Andreessen Horowitz to help developers identify and fix vulnerabilities in their AI applications. We're a small, dedicated team passionate about AI security and reliability.
Why Promptfoo?
- Impactful Work: Join us in creating the first pentesting product specifically targeting AI applications. We craft malicious inputs, simulate real-world threats, and push LLMs to their limits.
- Open-Source Commitment: We develop everything in the open, prioritizing transparency and community collaboration. Our work is entirely open-source, ensuring everyone can contribute and benefit.
- Perks: Fully remote, async-first culture, competitive salary + equity.
What You'll Do:
- Enhance our core evaluation framework, focusing on AI security.
- Develop features for prompt evaluation and automated red teaming of LLM applications.
- Collaborate with our open-source community and contribute to cutting-edge AI security practices.
- Gain hands-on experience with various LLMs, identifying vulnerabilities and improving robustness.
What We're Looking For:
- Proficiency in TypeScript, React, Node.js, and Python.
- Ability to ship features quickly and prioritize effectively.
- Interest in AI security, developer tools, and open-source contributions.
- Experience with LLM evaluations is a plus.
To Apply: Email careers@promptfoo.dev with "HN" in the subject. Include your GitHub/LinkedIn and a note on why you're excited about Promptfoo. Preference given to applicants with experience contributing to open-source projects.
Help us build the AI red team for everyone and make AI development safer and more reliable!
- Cygnus A is 232 Megaparsecs away[1], which converts to ~756,830,000 light-years away. Because of the expansion of the universe[2], what we observe happened slightly more recently.
Currently building out support for multi-agent evals, better tracing, voice, and static code analysis for AI security use cases. So many fun sub-problems in this space - LLM testing is deceptively hard.
If you end up checking it out and pick up an issue, I'll happily send swag. We're also hiring if you want to work on this stuff full-time.
https://github.com/promptfoo/promptfoo