Z

Zafran Security

AI-driven real-time cyber threat protection

Senior AI Engineer

AI Application Engineering +1Updated on Nov 18
Full-timeTel Aviv-Yafo, IsraelNo salary listedIn-person

About the Job

Requirements

  • At least 5 years of backend or infrastructure engineering experience, with strong system design skills.
  • Proven experience building and operating production-grade AI or large language model infrastructure for real users and traffic, including production incidents; prototype experience alone is insufficient.
  • Deep hands-on experience with agentic systems, including tool use, structured outputs, prompt and context management, retrieval, and long-running or streaming flows.
  • Experience designing and running large language model evaluations at scale.
  • Strong Python skills.
  • Production experience with AWS and Kubernetes, including observability through tracing, metrics, and logs.
  • An ownership mindset, treating the platform as a product and other engineers as its customers.

Responsibilities

  • Own the AI platform by designing, building, and running the shared agent runtime, including model access, tool use, memory and sessions, streaming, and human approval for sensitive actions.
  • Build production-grade scaling, model-provider fallback, rate limits, timeouts, and safe rollouts on Kubernetes.
  • Own and build the evaluation framework used by every team to measure quality, correctness, latency, and cost, and catch regressions in continuous integration before customers do.
  • Own observability and cost tracking, including tracing every agent run and tool call, tracking token spend per tenant and feature, and alerting when quality or cost drifts.
  • Own AI security, including strict tenant isolation, defenses against prompt injection, and guarded data access across a multi-tenant security platform.
  • Build MCP tools and data connectors that let agents query security data safely and reliably.
  • Enable R&D teams with shared libraries, templates, and documentation so they can independently build, test, deploy, and monitor AI features.
  • Remain hands-on with architecture, implementation, and production issues, and help raise the AI engineering standard across R&D.

Desired Qualifications

  • Experience with Amazon Bedrock, Strands Agents, LiteLLM, MCP, or OpenTelemetry.
  • Experience building internal developer infrastructure used by multiple engineering teams.
  • Experience with model evaluation, safety controls, governance, or large language model security, including guardrails and prompt injection.
  • Experience operating multi-tenant SaaS systems.
  • A background in cybersecurity or security-data products.
  • Familiarity with Go, Elasticsearch, ClickHouse, or PostgreSQL.

About the Company

Zafran Security

AI-driven real-time cyber threat protection

Zafran Security provides cybersecurity services to protect organizations from threats and vulnerabilities. It offers automated and AI-driven solutions to detect and mitigate security incidents in real time, targeting businesses of all sizes. Revenue comes from subscription-based services and customized security packages. The company is built on experienced security leadership, a team of security experts, and partnerships with investors to deliver risk mitigation and data protection. The goal is to help organizations quickly defuse threats, maintain business continuity, and safeguard digital environments.

Company size
51-200
Company stage
Series C
Total funding
$136M
Headquarters
New York City, New York
Founded
2022

Recently Posted Jobs

Explore more opportunities at Zafran Security

See more jobs