LLM Engineer (AI)

A high-growth Cybersecurity & AI startup developing an AI-native SOC automation platform. Driven by autonomous AI agents, the platform conducts end-to-end security alert investigations and attack pattern analysis at enterprise scale, automating complex manual analyst workflows for Fortune 500 enterprises and MSSPs.

Founded by experienced repeat entrepreneurs and backed by top-tier venture capital funds, the company operates its core R&D hub in Israel with around 40 employees.

Located in central Israel (walking distance from major train stations), operating on a hybrid work model with 2 days WFH per week.

Role Description-

• Joining the core AI engineering unit, developing and implementing LLM-based Autonomous Agents that power the platform’s decision-making engine.
• Leading full-lifecycle AI processes: from research and architecture selection to LLM agent orchestration, evaluation frameworks, and performance optimization.
• Deploying production-grade GenAI pipelines and agent frameworks meeting strict Enterprise SLA standards.
• Hands-on development in Python within Cloud-native environments, leveraging RAG, LangGraph/LangChain, and modern GenAI infrastructure.

Requirements-

• 5+ years of professional software development experience – Mandatory
• 1+ years of hands-on experience developing and deploying AI Agents / Autonomous LLM systems – Mandatory
• Strong proficiency in Python development – Mandatory
• Proven experience taking AI / LLM models into production environments – Mandatory
• Experience with AI orchestration frameworks (LangGraph, LangChain, LlamaIndex, etc.) and RAG architectures – Advantage
• Background in Cybersecurity, Threat Detection, SOC operations, or Enterprise SaaS – Advantage