LLM Engineer (AI)

A high-growth Cloud Security startup that has successfully raised tier-1 funding from the world's leading cybersecurity venture capital firms.

The company builds an innovative cloud infrastructure security platform that orchestrates operations-level data and translates it into highly contextual insights for information security squads.

By unifying distributed infrastructure layers into a single pane of glass, the platform dramatically reduces alert fatigue and optimizes threat mitigation for modern enterprise environments.

Located in the Tel Aviv region, the company maintains an energetic, high-velocity engineering culture and operates under a hybrid model providing one day of remote work per week.

Position Overview-

• Senior Backend & AI Infrastructure Engineer joining a brand-new, elite task force tasked with pioneering the company's end-to-end AI and Agentic workflow capabilities.
• Operating inside a blended team of AI specialists and Backend engineers, collaborating directly with the core Research division to embed intelligence across the enterprise security suite.
• Directing a hybrid technical architecture: 80% pure Backend & AI Infrastructure engineering (building production-grade systems, pipeline orchestration, and data frameworks in Python) and 20% GenAI Model & Logic engineering (authoring custom evaluation modules, agent logic, and prompt orchestration pipelines).
• Designing and scaling the core platform infrastructure required to run stable, production-ready Agentic Workflows capable of automated reasoning, contextual data analysis, and security remediation.
• Core Domain & Ecosystem- Python Development, Cloud Security Architecture, Large Language Models (LLMs), AI Agents & Multi-Agent Orchestration, LangChain, Production-Grade AI Infrastructure, Agent Logic, Evaluation Frameworks, and Scalable Backend Systems.

Requirements-

• 4 years of professional backend software development experience, with a heavy emphasis on production-grade programming (Python proficiency is highly preferred, but background in other robust backend languages is welcome) – Mandatory
• 1 years of proven, hands-on experience building and deploying autonomous AI Agents within enterprise software environments – Mandatory
• Proven, practical experience working with Large Language Models (LLMs) and building context-aware generative applications – Mandatory
• Technical familiarity or direct implementation experience with framework layers such as LangChain or equivalent orchestrators – Mandatory
• Strong foundational understanding of microservices architecture, infrastructure scaling, and API design – Mandatory