Senior Security Engineer II (ML)

The Role

Are you passionate about leveraging machine learning to scale-up security and privacy efforts? Do you have a keen understanding of security risks and a desire to innovate with cutting-edge ML solutions? Are you passionate about mitigating Agentic AI risks at scale? If so, Moveworks has an exciting opportunity for you.

As a Senior Security Engineer at Moveworks, you will be pivotal in fortifying our product's ML safeguards. Your focus will be on ensuring the effectiveness of ML safeguards (such as toxicity filter), AI Red Teaming testing efforts, among other ML security initiatives. You will not only focus on addressing challenges such as prompt injection attacks and prompt leaks, but also ensuring the proper implementation of new protocols such as Model Context Protocol and Agent2Agent while mitigating associated risks. Your work will enable the safe deployment of Large Language Models (LLMs) in enterprise environments, keeping us at the forefront of AI industry research.

You will also streamline essential security and privacy efforts with ML, including customer questionnaire completion, security/privacy reviews, and the evaluation of ML workflows. This role demands strategic thinking, strong coding skills, and the ability to deliver impactful solutions for our customers. Join us and play a critical role in the fastest-growing AI startup in its field.

What You Will Do

• Lead ML Security and Privacy Initiatives: Oversee security and privacy ML efforts at Moveworks (integrating advanced ML solutions to enhance our sales security motions and product security.) Train and fine-tune models within the security/privacy domain.
• Develop and Enhance AI Safeguards: Design, implement, and review AI safeguards and mitigations, requiring strong coding skills.
• Proficiency in ML: Safeguarding our usage of LLMs against issues like prompt injection, prompt leaks, toxicity, etc.
• Collaborate with Cross-Functional Teams: Work with machine learning, search, product, infrastructure, data, and frontend teams to design secure solutions. Automate security workflows, such as security questionnaires, using LLMs and AI.
• Stay Ahead of ML Trends: Monitor the evolving ML landscape to ensure the implementation of effective mitigations and safeguards.
• Define and Measure Security Metrics: Establish and track key security metrics to evaluate the effectiveness of our ML security and privacy program.

What You Bring to the Table

• 7+ years of experience in Security
• 1+ years in ML/AI security protections (such as prompt injection attacks).
• 4+ years of work experience in Golang, Python, or equivalent.
• Security Expertise: Ability to identify security risks, develop mitigation plans, and implement security features and solutions.
• Collaboration Skills: Experience building long-lasting relationships with teams.
• Technical Knowledge: Expert knowledge of AI/LLM security, authentication, authorization, identity systems, encryption, and secure coding practices.
• Cloud Infrastructure: Experience with cloud infrastructure like AWS, GCP, and/or Azure.
• Curiosity and Learning: A high level of curiosity about engineering outside of your immediate discipline and an incessant desire to learn.
• Compliance Experience: Experience operating in environments with compliance requirements (SOC2, HIPAA, ISO27001, FedRAMP, etc.).
• Educational Background: BS+ in computer science or a related field, or equivalent relevant experience.

If you are passionate about ML security and excited about the opportunity to make a significant impact at Moveworks, we encourage you to apply. Help us achieve our ambitious goals and maintain a high standard of security as we continue to grow and innovate in the AI space.