Work at Pattern Labs

Pattern Labs is a start-up at the forefront of AI risk evaluation and mitigation. Our mission is to solve AI security and we’re collaborating with top AI frontier labs and governments, among others, to achieve this. 
(For our hiring process, see below)

5 Open Positions

Cyber Researcher

As a cyber researcher at Pattern Labs, you will be at the forefront of research on AI security. You will engage with questions such as how to protect the weights of an advanced model against cyber threats, and how to evaluate cyber capabilities such as AI’s ability to exploit vulnerabilities, carry out network attacks, and develop malware. This role sits at a unique intersection of cybersecurity expertise and AI capabilities, where your background in vulnerability and security research will help shape the future of AI security.

Representative projects:

  • Expanding the quantity, quality, and variety of our cyber capabilities evaluation challenges (e.g. constructing original CTF-style vulnerability & exploitation challenges, network attack simulation challenges, and more, including original types of challenges).
  • Leading research into methods to mitigate cybersecurity risks related to the misuse of AI, the theft of model weights, or risks associated with integrating models with dangerous capabilities in AI agents.
  • Publishing your research and/or delivering research to our customers.
  • Advising and supporting the development of the products we’re building.

Representative research questions about AI frontier models:

  • Can an AI find and exploit 0-days?
  • What’s the best way to measure a CTF challenge's difficulty level vs. an AI player's skill level?
  • Can an AI elevate an average computer science student’s cyber capabilities to that of a nation-state?

You may be a good fit if you:

  • Have a strong background in vulnerability/security research & development such as having found vulnerabilities/CVEs, analyzed malware, researched detection methods for attacks, developed pentesting products or other attack tools, participated in CTF competitions or authored CTF challenges, or participated in other types of security research & development.
  • Work well in a multidisciplinary team and can adapt to rapidly evolving challenges.
  • Care about the societal impacts of your work.
Apply Now
Research Engineer

As a research engineer at Pattern Labs, you'll be at the forefront of building systems to evaluate and secure frontier AI models. You'll work on infrastructure and experiments to assess model capabilities, implement agent frameworks, and develop mitigations for advanced AI systems. Your role will involve creating robust evaluation pipelines, developing security-focused testing frameworks, and building tools that help understand and mitigate risks related to frontier models. You’ll have a chance to understand the research context and your code’s impact and contribute as a meaningful part of a growing team.

Representative projects:

  • Building a tool to continuously evaluate models and mitigate their risks. From designing the APIs for frontier labs, to building analysis and visualization tools that summarize 10,000+ transcripts into specific conclusions.
  • Designing and building challenges that measure a model’s ability to evade discovery, allowing us to see if models can operate on remote systems while avoiding detection by common defensive security tools.
  • Developing controlled environment frameworks for more secure use of frontier models.
  • Designing and building agents that improve a model’s ability to complete complex tasks. Includes many potential avenues, such as incorporating SOTA prompting practices, creating tools for task delegation, and more.
  • Publishing your research and/or delivering research to our customers.

You may be a good fit if you:

  • Have strong problem-solving and analytical skills.
  • Have strong production programming skills.
  • Work well in a multidisciplinary team and can adapt to rapidly evolving challenges.
  • Are interested in AI and cybersecurity (experience in machine learning or cybersecurity is a plus but not necessary).
  • Care about the societal impacts of your work.
Apply Now
AI Researcher

As an AI researcher at Pattern Labs, you'll be at the forefront of researching advanced frontier model capabilities and agent behavior, and help shape the future of AI security evaluation and mitigation. In this role, you will advance the frontier knowledge of AI and agentic frameworks, methods of assessing their ability, and mitigations for dangerous capabilities. 

Representative projects:

  • Researching capability elicitation methods to enhance model performance in evaluations.
  • Researching methodologies to assess generalization and coverage in model capabilities evaluation frameworks.
  • Contributing to academic publications and delivering research findings to customers.
  • Creating unique solutions to mitigate scenarios of AI loss of control or misalignment.
  • Advising and supporting the development of the products we’re building.

You may be a good fit if you:

  • Have a strong research experience in machine learning, particularly with frontier AI models.
  • Can design and implement novel research approaches for emerging AI challenges.
  • Work well in a multidisciplinary team and can adapt to rapidly evolving research questions.
  • Have a track record of publishing peer-reviewed research in top-tier venues (e.g., AAAI, ACL, EMNLP, ICLR, ICML, Nature, NeurIPS, Science, or similar).
  • Care about the societal impacts of your work.
Apply Now
Technical Policy Researcher

As a Technical Policy researcher at Pattern Labs, you'll tackle some of the biggest and most complex questions of AI development and deployment. Your work outlining problems, solutions and principles for governments, frontier labs, and deployers will shape the emerging field of AI security.

Representative projects:

  • Threat modeling and fleshing out in what specific way could a strong cyber-capable model cause harm.
  • Taxonomies for dangerous AI capabilities or mitigations.
  • Policy proposals for models' refusal policy (which prompts models should refuse to follow).
  • Following up on publications and news on AI policy, AI risks and mitigations, and technical AI research.
  • Writing academic papers and blog posts detailing our research around evaluation theory or mitigation recommendations.
  • Publishing your research and/or delivering research to our customers.

You may be a good fit if you have

  • Strong research skills in both quantitative and qualitative methods.
  • Strong writing skills, and experience as an academic (or industry equivalent) writer or analyst.
  • Interest in AI and specifically AI security.
  • Technical proficiency.
  • Background in AI/cybersecurity - a big advantage
Apply Now
Operations Facilitator

As an operations facilitator at Pattern Labs, you will handle a range of key operational processes, including vendor relations, compliance, contracts, day-to-day management, and internal policies. You will be instrumental in the company’s ability to scale and succeed at its mission to secure AI.

Representative projects:

  • Process and maintain vendor contracts and relationships.
  • Support compliance processes and documentation.
  • Track contract deliverables and deadlines.
  • Maintain internal policies and documentation.
  • Support recruiting and employee welfare processes.
  • Run day-to-day ops.

You may be a good fit if you have

  • Experience in streamlining and scaling internal processes.
  • Strong organizational skills and extremely high attention to detail.
  • Strong communication skills.
  • Tech industry, specifically start-up experience - an advantage.
  • Background in HR, Legal or financial domains- an advantage.
Apply Now

Hiring Process

The hiring process at Pattern Labs varies based on role and candidate, but our standard process will include the following stages:

  1. Job Application. CV and additional information submitted via this link.
  2. Brief Exploratory Chat. A 15-minute online chat with one of our team members to discuss your interests and experience and for candidates to learn more about Pattern Labs.
  3. Take-Home Assignment. Assignments usually take ±5 hours, depending on the role. 
  4. In-Depth Exploratory Chat. A deeper, face-to-face conversation with a senior team member.
  5. Interviews Day. 2-3 one hour to an hour and a half technical interviews. Plus, an organizational fit interview with a member of our leadership. Often, the technical interviews and fit interviews will be done on different dates to accommodate mutual scheduling needs. These interviews are usually done at our office.
  6. References. We typically ask for 3 references from different organizations / roles, but pending on circumstances 2 references could suffice. 
  7. Offer. We’ll contact prospective candidates with an offer.

Note: 
1. We included multiple steps to inform our hiring decisions better (even though, as mentioned, not all people go through all of the steps). We recognize that going through the process requires time and effort; nonetheless, we think that using a variety of tools (tests, interviews, reference checks, etc.) is essential to reduce biases and help you showcase your strengths. In this spirit, we will do our best to accommodate requests to set each stage at a convenient time.
2. As mentioned above, what we describe is our standard process. Depending on the role and circumstances, we may decide to add a stage or skip multiple stages. We deeply value your time – that's why we are firmly committed to not adding more than one additional stage beyond what's outlined above.
3. While we have several steps in our process, we can move things along swiftly! If you're working with a specific timeline, just let us know as soon as possible. We'll do our best to make it work for you.
4. To make the process maximally useful to you, you should feel very comfortable asking us questions about Pattern Labs in any conversation, and we plan the interviews to include enough time for you to do that.