AI Security Engineer - GenAI Platforms
United States,
New York
Permanent
Job ID: 2539
Job Description
[Up to c. $300k Base Salary + Discretionary Bonus | Office-Led Working - Likely 4 Days in Office]
Role Overview
A leading global investment firm is building out its AI security capability as GenAI becomes more deeply embedded across internal platforms, engineering workflows and business-critical technology. This is a hands-on engineering role focused on securing production AI systems, agentic workflows, internal tools and cloud-native platforms across a high-calibre technology environment...
Key Responsibilities
- Design and build security controls for internal GenAI applications, APIs, model usage patterns and platform integrations
- Secure agentic AI, tool-calling and connector-based workflows, including MCP-style integrations and privileged system access
- Lead technical threat modelling across prompt injection, jailbreaks, data leakage, tool abuse, model misuse and AI supply-chain risk
- Define secure reference patterns for cloud-native and hybrid GenAI workloads, including secrets, network boundaries and service isolation
- Build monitoring and detection logic for unusual AI behaviour, unsafe outputs, suspicious tool activity and potential data exposure
- Support response and remediation for incidents involving AI-enabled applications, internal platforms or sensitive information
- Translate AI security requirements into practical engineering controls, evidence, testing and audit-ready documentation
- Act as a technical AI security partner to engineering, infrastructure, MLOps, product, legal, compliance and business stakeholders
What You’ll Bring…
- 5+ years of software engineering, product security, application security or security engineering experience, with strong hands-on coding in Python, Go, Java or similar
- Practical experience with AI/ML or GenAI technologies, ideally including LLM applications, RAG, agents, tool-calling, model APIs or AI platform infrastructure
- Strong understanding of AI security risks, including prompt injection, unsafe tool execution, data exfiltration, jailbreaks, training data leakage and supply-chain exposure
- Experience building, deploying or securing containerised services using Kubernetes
- Ability to design and deliver production-grade security controls without slowing down engineering delivery
- Strong threat-modelling capability across modern software, cloud, API, data and AI-enabled systems
- Experience working with CI/CD, infrastructure pipelines, DevOps, MLOps or platform engineering teams
- Clear communication style, with the ability to influence technical and non-technical stakeholders in a high-performance environment
- (Preferred) Financial services, hedge fund, trading, fintech or other highly regulated technology environment experience
- (Preferred) Experience with MCP, LangChain, LlamaIndex, Bedrock, OpenAI/Azure OpenAI, Vertex AI, vector databases or AI gateway/guardrail tooling
- (Preferred) Experience building detection, observability or incident-response workflows for AI, cloud or application security events
...
Apply for this role
All fields marked with * are required.