Staff AI Security Engineer

Spring Health is a global mental health company on a mission to eliminate every barrier to mental health. We're building a world where getting support is simple, personal, and built around the person, so care can continue through every job, move, health plan, and life stage.

Our AI-native platform helps us deliver personalized support across self-guided tools, coaching, therapy, medication management, and specialty care. With outcomes independently validated by JAMA Network Open and the Validation Institute, Spring Health reaches more than 170 million people worldwide through leading employers, health plans, and partners.

As an AI-native company, we believe technology should expand the reach, quality, and humanity of care. Every Spring Health team member is expected to use AI tools thoughtfully, apply human judgment to AI outputs, and keep building AI fluency in ways that support their role and our mission.

We are actively seeking a Staff AI Security Engineer to join our team. Reporting to the CISO, you will define and evolve our AI security strategy to protect highly sensitive mental health data across both product and corporate environments. 

Please note that this is a hybrid role based in San Francisco, with an expectation to be in the office 2–3 days per week at our 44 Montgomery Street location. Candidates must be based in the San Francisco metro area or able to relocate independently within 90 days of their start date. Occasional travel will be required for team on-sites.

• →Define and evolve our AI security strategy to protect highly sensitive mental health data across both product and corporate environments
• →Lead secure design and threat modeling for AI systems including LLMs, agentic workflows, and retrieval pipelinesIdentify and mitigate risks such as prompt injection, data exfiltration, model abuse, and privilege escalation
• →Build scalable AI security guardrails and tooling that enable safe experimentation across engineering and business teams
• →Establish AI-specific governance frameworks covering identity, access control, auditability, and observability
• →Take ownership of and lead our AI Red Team to proactively identify vulnerabilities
• →Design and implement AI observability pipelines to detect anomalous model behavior and policy violations in near real-time
• →Develop and operationalize AI incident response playbooks to ensure rapid containment of security events
• →Partner with product and engineering teams to enable responsible AI innovation in a hyper-growth environment
• →Champion a culture of secure AI development by mentoring engineers and defining high standards for the organization

• 80% of new AI product features are threat modeled prior to GA
• 80% of AI features are tested by the AI Red Team or equivalent adversarial testing before GA
• Achieve >=70% coverage of production AI features with automated LLM vulnerability testing
• Grow participation in the AI Red Team by 10% YoY
• Develop AI incident response playbooks and conduct at least one AI-focused tabletop or live simulation per year

• 10+ years experience in a software engineering discipline, with at least 5+ years focused on security
• Hands-on experience securing AI/ML systems, including practical AI red teaming against LLMs, agentic workflows, or RAG systems
• Experience developing or implementing automated LLM vulnerability testing for prompt injection and data exfiltration
• Strong foundation in application security principles, threat modeling, secure design, and identity and access control
• Demonstrated ability to build tools and automation with a developer mindset
• Experience influencing senior engineers and cross-functional stakeholders across product, legal, and compliance
• Proven track record of mentoring engineers and cultivating a strong security culture across an organization
• Strong working knowledge of modern developer tooling, CI/CD pipelines, and git-based collaboration
• Ability to operate in ambiguity and translate emerging AI risks into pragmatic, scalable security controls
• Deep personal ownership and a passion for advancing AI security through continuous learning

The target base salary range for this position is $239,200 - $270,000, and is part of a competitive total rewards package including stock options and benefits. Individual pay may vary from the target range and is determined by a number of factors including experience, location, internal pay equity, and other relevant business considerations. We review all employee pay and compensation programs annually using Radford Global Compensation Database at minimum to ensure competitive and fair pay.