This is adversarial work: attackers adapt constantly, and we build the detection systems, heuristics, and automated responses that stay ahead of them.

What makes this role unique is the AI-native nature of Replit's platform. You'll work on problems that barely exist elsewhere: building guardrails for AI-generated code, detecting prompt injection attacks at scale, and using LLMs as a defensive tool against abuse.

If you want hands-on experience applying AI to security problems, this is one of the few places you can do it in production with real attackers. You'll own problems end-to-end, from identifying emerging abuse patterns to shipping the systems that stop them at scale.

Responsibilities

• Design and implement LLM guardrails that detect abuse scenarios in AI-generated code and agent interactions
• Build AI-powered detection systems that use LLMs to identify malicious patterns, classify threats, and automate response decisions
• Build and operate abuse detection systems that identify phishing, cryptomining, account takeover, and financial fraud across millions of daily user actions
• Design automated response mechanisms that enforce platform policies without manual intervention
• Own the full abuse response lifecycle: detection, investigation, enforcement, and handling appeals alongside Support and Legal
• Analyze attack patterns using BigQuery and Hex, turning investigation findings into new detection rules
• Maintain and extend internal detection tools (Slurper, Netwatch) that continuously monitor user activity
• Integrate and tune security scanners (SAST, SCA) in CI pipelines with tight performance SLAs
• Track abuse trends, measure detection effectiveness, and adapt defenses as attack patterns evolve

Requirements

• 8+ years of experience in security engineering, anti-abuse, trust & safety, or fraud detection
• Strong programming skills in Python and/or TypeScript for building detection systems and automation
• Experience with SQL and data analysis at scale (BigQuery, Snowflake, or similar)
• Experience building or fine-tuning ML/LLM-based classifiers for security or abuse detection
• Familiarity with prompt injection, jailbreaking, and other LLM-specific attack vectors
• Ability to investigate complex abuse patterns and translate findings into automated defenses
• Familiarity with common attack patterns: phishing infrastructure, account takeover, credential stuffing, resource abuse
• Clear communication skills for working across Security, Support, Legal, and Engineering teams

Nice to Have

• Experience at a platform company dealing with user-generated content or compute abuse (hosting providers, cloud platforms, developer tools)
• Background in fraud detection, payment abuse, or financial crime
• Familiarity with device fingerprinting, IP reputation, and email validation services
• Experience with CI/CD security tooling (SAST, SCA, Dependabot, Snyk)
• Knowledge of container security, Linux internals, or cloud infrastructure (GCP preferred)
• Prior work with abuse reporting pipelines, trust & safety tooling, or content moderation systems

Tools + Tech Stack for this role

• Languages: Python, TypeScript, Go, SQL
• Data: BigQuery, Hex
• Detection tools: Slurper, Netwatch, Stytch (device fingerprint); ClearOut (email reputation)
• CI/CD Security: Dependabot, Snyk, SAST/SCA scanners
• Infrastructure: GCP, Kubernetes
• Collaboration: Linear, Slack, Zendesk (for abuse reports)

XML job scraping automation by YubHub

As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

This role is part of Microsoft AI’s Superintelligence Team. The MAIST is a startup-like team inside Microsoft AI, created to push the boundaries of AI toward Humanist Superintelligence , ultra-capable systems that remain controllable, safety-aligned, and anchored to human values.

Our mission is to create AI that amplifies human potential while ensuring humanity remains firmly in control. We aim to deliver breakthroughs that benefit society , advancing science, education, and global well-being.

We are hiring a Product Manager to own AI model security , the discipline of making our frontier models resilient against adversarial attack and purpose-built for security practitioners.

This role has a dual mandate: (1) harden our models against the full spectrum of LLM security threats , prompt injection, data exfiltration, jailbreaking, training data extraction, zero-day exploit generation, model poisoning, and agentic workflow exploitation , and (2) partner closely with Microsoft Security product teams (Azure Security, Security Copilot) to ensure our models deliver best-in-class capabilities for real-world security workflows.

Responsibilities:

Own the model security roadmap: Define and prioritize the security hardening strategy for our frontier models across the full OWASP LLM threat surface , prompt injection (direct and indirect), data exfiltration, jailbreak resistance, system prompt leakage, training data extraction, and adversarial manipulation of agentic workflows.

Drive zero-day and exploit defense: Work with researchers to evaluate and mitigate the risk of models being used to generate zero-day exploits, malware, or novel attack vectors.

Build and scale red-teaming frameworks: Design, run, and iterate adversarial testing programs , both automated and human-driven , to continuously probe model vulnerabilities.

Establish metrics (e.g., jailbreak success rate, injection bypass rate, exfiltration resistance) and drive measurable improvement over time.

Partner with Microsoft Security product teams: Work closely with Azure Security and Security Copilot teams to translate their product requirements into model training priorities.

Ensure our models are purpose-built for threat detection, incident triage, vulnerability assessment, log analysis, and compliance reasoning.

Define security-specific model evaluations: Build benchmark suites and evaluation frameworks that measure real-world security usefulness , not just academic performance.

Drive training data strategy to improve domain-specific model quality for security practitioners.

Shape security policy and launch readiness: Establish clear security criteria for model launches.

Own the security dimension of go/no-go decisions, with frameworks that balance capability, risk, and deployment context.

Stay at the frontier: Track the rapidly evolving LLM security landscape , new attack techniques, emerging standards (OWASP, NIST AI RMF), regulatory requirements (EU AI Act), and academic research.

Translate what you learn into actionable product priorities.

Influence model training and architecture: Partner with researchers and engineers to embed security considerations into model training, fine-tuning, RLHF, and post-training safeguards.

Qualifications:

Bachelor’s Degree AND 5+ years experience in product management, security engineering, or software development OR equivalent experience

Demonstrated hands-on experience with AI/ML systems , you have personally built, evaluated, or shipped ML-powered products or security tools

Deep familiarity with LLM security threats: prompt injection, jailbreaking, data exfiltration, adversarial attacks on generative models , through professional experience, red-teaming, or security research

Experience defining product requirements and driving decisions in partnership with researchers or ML engineers

Track record of building evaluation systems, security benchmarks, or adversarial testing frameworks , not just consuming them

Ability to operate autonomously, make decisions with incomplete information, and drive projects from ambiguity to shipped outcomes

Preferred Qualifications:

Technical background in computer science, security, or AI/ML , a postgraduate degree is a plus but not required

Experience in offensive security, penetration testing, or red teaming , ideally applied to AI/ML systems

Familiarity with security workflows and tooling (SIEM, SOAR, EDR, threat intelligence platforms) and how practitioners use them in production

Understanding of the model lifecycle (pre-training, fine-tuning, RLHF, deployment, monitoring) and where security interventions are most effective

Experience working with or within enterprise security organizations (e.g., Microsoft Security, CrowdStrike, Palo Alto Networks, or similar)

Published research, blog posts, or public contributions in AI security, adversarial ML, or LLM red teaming

XML job scraping automation by YubHub

As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

This role is part of Microsoft AI’s Superintelligence Team. The MAIST is a startup-like team inside Microsoft AI, created to push the boundaries of AI toward Humanist Superintelligence , ultra-capable systems that remain controllable, safety-aligned, and anchored to human values.

Our mission is to create AI that amplifies human potential while ensuring humanity remains firmly in control. We aim to deliver breakthroughs that benefit society , advancing science, education, and global well-being.

We are hiring a Product Manager to own AI model security , the discipline of making our frontier models resilient against adversarial attack and purpose-built for security practitioners.

This role has a dual mandate: (1) harden our models against the full spectrum of LLM security threats , prompt injection, data exfiltration, jailbreaking, training data extraction, zero-day exploit generation, model poisoning, and agentic workflow exploitation , and (2) partner closely with Microsoft Security product teams (Azure Security, Security Copilot) to ensure our models deliver best-in-class capabilities for real-world security workflows.

Responsibilities:

Own the model security roadmap: Define and prioritize the security hardening strategy for our frontier models across the full OWASP LLM threat surface , prompt injection (direct and indirect), data exfiltration, jailbreak resistance, system prompt leakage, training data extraction, and adversarial manipulation of agentic workflows.

Drive zero-day and exploit defense: Work with researchers to evaluate and mitigate the risk of models being used to generate zero-day exploits, malware, or novel attack vectors.

Build and scale red-teaming frameworks: Design, run, and iterate adversarial testing programs , both automated and human-driven , to continuously probe model vulnerabilities.

Establish metrics (e.g., jailbreak success rate, injection bypass rate, exfiltration resistance) and drive measurable improvement over time.

Partner with Microsoft Security product teams: Work closely with Azure Security and Security Copilot teams to translate their product requirements into model training priorities.

Ensure our models are purpose-built for threat detection, incident triage, vulnerability assessment, log analysis, and compliance reasoning.

Define security-specific model evaluations: Build benchmark suites and evaluation frameworks that measure real-world security usefulness , not just academic performance.

Drive training data strategy to improve domain-specific model quality for security practitioners.

Shape security policy and launch readiness: Establish clear security criteria for model launches.

Own the security dimension of go/no-go decisions, with frameworks that balance capability, risk, and deployment context.

Stay at the frontier: Track the rapidly evolving LLM security landscape , new attack techniques, emerging standards (OWASP, NIST AI RMF), regulatory requirements (EU AI Act), and academic research.

Translate what you learn into actionable product priorities.

Influence model training and architecture: Partner with researchers and engineers to embed security considerations into model training, fine-tuning, RLHF, and post-training safeguards.

Qualifications:

Bachelor’s Degree AND 5+ years experience in product management, security engineering, or software development OR equivalent experience

Demonstrated hands-on experience with AI/ML systems , you have personally built, evaluated, or shipped ML-powered products or security tools

Deep familiarity with LLM security threats: prompt injection, jailbreaking, data exfiltration, adversarial attacks on generative models , through professional experience, red-teaming, or security research

Experience defining product requirements and driving decisions in partnership with researchers or ML engineers

Track record of building evaluation systems, security benchmarks, or adversarial testing frameworks , not just consuming them

Ability to operate autonomously, make decisions with incomplete information, and drive projects from ambiguity to shipped outcomes

XML job scraping automation by YubHub

Start with an opening paragraph (no heading): what the role is, who the company is, why it matters. If the ad mentions salary, include it here.

Rephrase bullet points in your own words while keeping the factual content. Combine related points where it makes sense.

For benefits/perks: gather them from anywhere in the ad into one section. If the ad mentions nothing about benefits, omit a benefits section entirely.

Do not invent information that is not in the original ad.

About the role The Anti-Abuse team is the front line defending Replit's platform from exploitation. We detect and shut down phishing deployments, prevent cryptomining on free-tier infrastructure, stop LLM token farming, and keep bad actors from weaponizing the platform against our users. This is adversarial work: attackers adapt constantly, and we build the detection systems, heuristics, and automated responses that stay ahead of them.

What makes this role unique is the AI-native nature of Replit's platform. You'll work on problems that barely exist elsewhere: building guardrails for AI-generated code, detecting prompt injection attacks at scale, and using LLMs as a defensive tool against abuse. If you want hands-on experience applying AI to security problems, this is one of the few places you can do it in production with real attackers. You'll own problems end-to-end, from identifying emerging abuse patterns to shipping the systems that stop them at scale.

In this role you will…

• Design and implement LLM guardrails that detect abuse scenarios in AI-generated code and agent interactions
• Build AI-powered detection systems that use LLMs to identify malicious patterns, classify threats, and automate response decisions
• Build and operate abuse detection systems that identify phishing, cryptomining, account takeover, and financial fraud across millions of daily user actions
• Design automated response mechanisms that enforce platform policies without manual intervention
• Own the full abuse response lifecycle: detection, investigation, enforcement, and handling appeals alongside Support and Legal
• Analyze attack patterns using BigQuery and Hex, turning investigation findings into new detection rules
• Maintain and extend internal detection tools (Slurper, Netwatch) that continuously monitor user activity
• Integrate and tune security scanners (SAST, SCA) in CI pipelines with tight performance SLAs
• Track abuse trends, measure detection effectiveness, and adapt defenses as attack patterns evolve

Required skills and experience:

• 4+ years of experience in security engineering, anti-abuse, trust & safety, or fraud detection
• Strong programming skills in Python and/or TypeScript for building detection systems and automation
• Experience with SQL and data analysis at scale (BigQuery, Snowflake, or similar)
• Experience building or fine-tuning ML/LLM-based classifiers for security or abuse detection
• Familiarity with prompt injection, jailbreaking, and other LLM-specific attack vectors
• Ability to investigate complex abuse patterns and translate findings into automated defenses
• Familiarity with common attack patterns: phishing infrastructure, account takeover, credential stuffing, resource abuse
• Clear communication skills for working across Security, Support, Legal, and Engineering teams.

Nice to have:

• Experience at a platform company dealing with user-generated content or compute abuse (hosting providers, cloud platforms, developer tools)
• Background in fraud detection, payment abuse, or financial crime
• Familiarity with device fingerprinting, IP reputation, and email validation services
• Experience with CI/CD security tooling (SAST, SCA, Dependabot, Snyk)
• Knowledge of container security, Linux internals, or cloud infrastructure (GCP preferred)
• Prior work with abuse reporting pipelines, trust & safety tooling, or content moderation systems

Tools + Tech Stack for this role

• Languages: Python, TypeScript, Go, SQL
• Data: BigQuery, Hex
• Detection tools: Slurper, Netwatch, Stytch (device fingerprint); ClearOut (email reputation)
• CI/CD Security: Dependabot, Snyk, SAST/SCA scanners
• Infrastructure: GCP, Kubernetes
• Collaboration: Linear, Slack, Zendesk (for abuse reports)

This role may _not_ be a fit if

• You prefer deep security research over building operational detection systems
• You want to focus on vulnerability management, pentesting, or bug bounty triage (that's our Security team)
• You're looking for a role with predictable, well-defined problems rather than constantly adapting to adversarial behavior
• You prefer working in isolation rather than partnering closely with Support, Legal, and cross-functional teams
• You're uncomfortable making enforcement decisions that affect real users

_This is a full-time role that can be held from our Foster City, CA office. The role has an in-office requirement of Monday, Wednesday, and Friday._

Full-Time Employee Benefits Include: 💰 Competitive Salary & Equity 💹 401(k) Program with a 4% match ⚕️ Health, Dental, Vision and Life Insurance 🩼 Short Term and Long Term Disability 🚼 Paid Parental, Medical, Caregiver Leave 🚗 Commuter Benefits 📱 Monthly Wellness Stipend 🧑‍💻 Autonomous Work Environment 🖥 In Office Set-Up Reimbursement 🏝 Flexible Time Off (FTO) + Holidays 🚀 Quarterly Team Gatherings ☕ In Office Amenities

XML job scraping automation by YubHub