Security Engineer LLM SecOps
Posted
Job Title: Security Engineer - LLM SecOps
Location: Hybrid most remotely with ability to travel to California or NY when needed
Project Duration: May to December (with potential extension)
Interview: Video
Need banking / financial services / payments experience
Overview
We are seeking a Security Engineer specializing in LLM SecOps to join a Product Security Engineering team within a leading US-based fintech organization. This role focuses on securing AI/LLM-powered systems embedded in customer-facing and internal platforms, operating at scale in a regulated financial environment.
Unlike traditional security roles, this position works directly with engineering teams to design and implement security controls within AI inference pipelines, ensuring data protection, model integrity, and real-time performance.
Key Responsibilities
Required Qualifications
LLM Security
Location: Hybrid most remotely with ability to travel to California or NY when needed
Project Duration: May to December (with potential extension)
Interview: Video
Need banking / financial services / payments experience
Overview
We are seeking a Security Engineer specializing in LLM SecOps to join a Product Security Engineering team within a leading US-based fintech organization. This role focuses on securing AI/LLM-powered systems embedded in customer-facing and internal platforms, operating at scale in a regulated financial environment.
Unlike traditional security roles, this position works directly with engineering teams to design and implement security controls within AI inference pipelines, ensuring data protection, model integrity, and real-time performance.
Key Responsibilities
- Design and implement guardrail systems for securing LLM inputs and outputs in production environments
- Secure Retrieval-Augmented Generation (RAG) pipelines, vector databases, and embedding workflows
- Develop runtime monitoring solutions for AI systems, including prompt logging, context analysis, and response validation
- Secure LLM API endpoints through authentication, rate limiting, and abuse prevention mechanisms
- Detect and respond to AI-related security incidents using structured Root Cause Analysis (RCA) methodologies
- Manage AI supply chain risks, including third-party models, APIs, and plugin integrations
- Collaborate closely with Product Security, Machine Learning Engineering, and Platform teams.
Required Qualifications
LLM Security
- Experience with prompt injection defense, jailbreak detection, and output filtering
- Familiarity with OWASP Top 10 for LLM Applications
- Knowledge of vector database security and embedding pipeline protection
- Experience with data isolation in multi-tenant environments and PII protection
- Experience with logging, anomaly detection, and SIEM integration for AI systems
- Strong understanding of incident response frameworks and RCA practices
- Hands-on experience with AWS environments
- Knowledge of Kubernetes security, container isolation, and IAM/RBAC models
- Experience securing APIs using OAuth, JWT, and rate limiting techniques
- Strong proficiency in Python for automation, scripting, and security tooling
- Experience in fintech, payments, or regulated financial services environments
- Exposure to AI security platforms such as Lakera, Protect AI, HiddenLayer, or similar tools
- Relevant certifications (e.g., AWS Security Specialty, CISSP, OSCP)
- Familiarity with regulatory and data protection frameworks (e.g., PCI-DSS, FCRA)
- Cloud: AWS (EKS, Aurora MySQL)
- Data Processing: Apache Spark
- Backend: Python, Kotlin
- Frontend: JavaScript, TypeScript, React / React Native
- Security & Operations: mTLS, CDN/Edge Security, SLI/SLO frameworks, RCA practices
