עדיין מחפשים עבודה במנועי חיפוש? הגיע הזמן להשתדרג!
במקום לעבור לבד על אלפי מודעות, Jobify מנתחת את קורות החיים שלך ומציגה לך רק משרות שבאמת מתאימות לך.
מעל 80,000 משרות • 4,000 חדשות ביום
חינם. בלי פרסומות. בלי אותיות קטנות.
מלאה
30,000-45,000 ₪
we are looking for a AI Security Engineer.
As AI capabilities accelerate across the bank, we need an engineer to design and enforce safe AI usage-protecting customer data, preserving model integrity, and meeting our regulatory obligations. You'll be the architect of guardrails, tooling, and policies that make AI both secure and useful for product and internal teams. This isn't about slowing things down; it's about building the trust layer that lets innovation move fast without breaking things.
What Youll Actually Be Doing:
Design enterprise AI guardrails across Azure and AWS (e.g., Azure AI Studio/Azure OpenAI, Amazon Bedrock/SageMaker): content filtering, PII redaction, prompt/response validation, and policy enforcement services.
Implement data minimization controls for GenAI/RAG workloads: context filtering, least‐privileged retrieval, document-level ACL enforcement, vector store hardening, and secure token/secret handling.
Threat model AI systems (apps, agents, RAG, fine-tuning pipelines) using frameworks like STRIDE and the OWASP Top 10 for LLM Apps; define misuse scenarios (prompt injection/jailbreaks/data exfiltration) and build mitigations.
Build monitoring and telemetry: privacy-preserving prompt/response logging, sensitive-data detection, safety/eval dashboards, drift/abuse signals, and incident hooks into our SIEM.
Integrate AI security into the SDLC: reusable libraries, pre-commit checks, CI/CD gates, policy-as-code, and secure-by-default reference architectures for product teams.
Evaluate third‑party AI vendors and internal apps: security reviews, data residency and retention requirements, SSO/SCIM integrations, DPA/TPRM inputs, and continuous control testing.
Partner across Security, Data, Privacy, and Engineering to map AI controls to FFIEC, SOC 2, and PCI DSS; document control evidence for audits.
Lead/participate in AI red‑teaming: automated jailbreak/prompt‑injection tests, safety benchmarks, purple‑team exercises, and response playbooks for AI incidents.
Enable the org with concise guidelines, examples, and training on safe AI development and usage.
As AI capabilities accelerate across the bank, we need an engineer to design and enforce safe AI usage-protecting customer data, preserving model integrity, and meeting our regulatory obligations. You'll be the architect of guardrails, tooling, and policies that make AI both secure and useful for product and internal teams. This isn't about slowing things down; it's about building the trust layer that lets innovation move fast without breaking things.
What Youll Actually Be Doing:
Design enterprise AI guardrails across Azure and AWS (e.g., Azure AI Studio/Azure OpenAI, Amazon Bedrock/SageMaker): content filtering, PII redaction, prompt/response validation, and policy enforcement services.
Implement data minimization controls for GenAI/RAG workloads: context filtering, least‐privileged retrieval, document-level ACL enforcement, vector store hardening, and secure token/secret handling.
Threat model AI systems (apps, agents, RAG, fine-tuning pipelines) using frameworks like STRIDE and the OWASP Top 10 for LLM Apps; define misuse scenarios (prompt injection/jailbreaks/data exfiltration) and build mitigations.
Build monitoring and telemetry: privacy-preserving prompt/response logging, sensitive-data detection, safety/eval dashboards, drift/abuse signals, and incident hooks into our SIEM.
Integrate AI security into the SDLC: reusable libraries, pre-commit checks, CI/CD gates, policy-as-code, and secure-by-default reference architectures for product teams.
Evaluate third‑party AI vendors and internal apps: security reviews, data residency and retention requirements, SSO/SCIM integrations, DPA/TPRM inputs, and continuous control testing.
Partner across Security, Data, Privacy, and Engineering to map AI controls to FFIEC, SOC 2, and PCI DSS; document control evidence for audits.
Lead/participate in AI red‑teaming: automated jailbreak/prompt‑injection tests, safety benchmarks, purple‑team exercises, and response playbooks for AI incidents.
Enable the org with concise guidelines, examples, and training on safe AI development and usage.
Requirements:
5+ years in Security Engineering/AppSec/Cloud Security (or similar), including 1-2+ years securing AI/ML or data‑intensive systems (GenAI preferred).
Hands‑on experience with AWS and/or Azure and modern app stacks (Python/TypeScript, REST/gRPC, containers/Kubernetes, IaC such as Terraform).
Practical understanding of LLM attack surfaces (prompt injection, data leakage via tools, training/fine‑tune poisoning, model supply chain) and mitigation patterns.
Familiarity with identity and access for AI workloads (OAuth2/OIDC, service principals, role tokens, PIM), and secure secret management/KMS.
Experience implementing observability/telemetry and routing findings to SIEM; comfort balancing privacy with traceability.
Ability to translate controls into developer-friendly libraries, docs, and CI/CD checks; strong written communication in English and Hebrew.
Comfort working in a regulated environment and mapping controls to frameworks (FFIEC, SOC 2, PCI DSS).
Nice to have:
Financial services background or other high‑assurance domains.
Exposure to Duende IdentityServer, SSO/SCIM, and enterprise authorization patterns.
Experience with vector databases (e.g., OpenSearch, pgvector, Pinecone) and secure RAG architectures.
Familiarity with guardrail tooling (e.g., Azure AI Safety features, Amazon Bedrock Guardrails) and policy engines (OPA/Rego).
Prior work in AI red‑teaming or safety evaluation harnesses; contributions to OSS or published talks.
5+ years in Security Engineering/AppSec/Cloud Security (or similar), including 1-2+ years securing AI/ML or data‑intensive systems (GenAI preferred).
Hands‑on experience with AWS and/or Azure and modern app stacks (Python/TypeScript, REST/gRPC, containers/Kubernetes, IaC such as Terraform).
Practical understanding of LLM attack surfaces (prompt injection, data leakage via tools, training/fine‑tune poisoning, model supply chain) and mitigation patterns.
Familiarity with identity and access for AI workloads (OAuth2/OIDC, service principals, role tokens, PIM), and secure secret management/KMS.
Experience implementing observability/telemetry and routing findings to SIEM; comfort balancing privacy with traceability.
Ability to translate controls into developer-friendly libraries, docs, and CI/CD checks; strong written communication in English and Hebrew.
Comfort working in a regulated environment and mapping controls to frameworks (FFIEC, SOC 2, PCI DSS).
Nice to have:
Financial services background or other high‑assurance domains.
Exposure to Duende IdentityServer, SSO/SCIM, and enterprise authorization patterns.
Experience with vector databases (e.g., OpenSearch, pgvector, Pinecone) and secure RAG architectures.
Familiarity with guardrail tooling (e.g., Azure AI Safety features, Amazon Bedrock Guardrails) and policy engines (OPA/Rego).
Prior work in AI red‑teaming or safety evaluation harnesses; contributions to OSS or published talks.
This position is open to all candidates.
במקום לעבור לבד על אלפי מודעות, Jobify מנתחת את קורות החיים שלך ומציגה לך רק משרות שבאמת מתאימות לך.
מעל 80,000 משרות • 4,000 חדשות ביום
חינם. בלי פרסומות. בלי אותיות קטנות.
רמת גן
