דרושים»הנדסה» Senior AI Engineer

לפני 18 שעות חברה חסויה Location: Job Type: We are looking for a Senior AI Engineer to join our Cybersecurity team in Tel Aviv. You will design, build, and productionize LLM-powered applications, multi-agent systems, and MLOps infrastructure that power our company's next-generation cybersecurity capabilities. This is a high-impact, hands-on role at the intersection of applied AI, agentic systems, and network securit What You'll Do Design and develop LLM-powered security features and internal AI tools, including RAG pipelines, multi-agent workflows, and prompt-engineered systems tailored for cybersecurity use cases Architect and operate multi-agent systems in production - including agent orchestration, inter-agent communication, task delegation, and failure handling at scale Build robust agent monitoring and observability pipelines: tracing agent execution, detecting drift or failure, alerting on anomalous behavior, and maintaining agent reliability SLAs Build and maintain scalable MLOps infrastructure: model serving, evaluation frameworks, experiment tracking, and CI/CD for ML models Work with internal datasets (network telemetry, security logs, threat intelligence) to fine-tune and adapt foundation models for domain-specific detection and response tasks Partner with the Cybersecurity, R&D, and infrastructure teams to define AI-driven security features and deliver them end-to-end Establish best practices for model observability, safety, and responsible AI deployment within the organization Stay current with the fast-moving LLM/GenAI and agentic AI ecosystem and evaluate emerging frameworks, models, and tools for adoption.Requirements: Must-Have 5-8 years of software engineering experience, with at least 2-3 years focused on AI/ML engineering Hands-on experience building production-grade LLM applications - RAG, agents, tool use, or fine-tuning Proven experience deg and running multi-agent systems in production: orchestration patterns, agent state management, retries, and graceful degradation Experience monitoring and observing AI agents in production - execution tracing, latency tracking, failure detection, and alerting (e.g., LangSmith, Arize, custom observability stacks) Proficiency with agentic frameworks: LangChain, LangGraph, and/or AWS Bedrock AgentCore Strong Python skills and comfort working across the full AI application stack Experience deg and operating MLOps pipelines (model versioning, deployment, monitoring) Solid understanding of transformer-based models, embeddings, and vector databases (e.g., Pinecone, Weaviate, pgvector) Comfortable working in cloud environments (AWS, GCP, or Azure) and containerized deployments (Docker, Kubernetes) Strong problem-solving skills and ability to work autonomously in a fast-paced environment Nice-to-Have Background in cybersecurity - threat detection, SIEM, SOC automation, or security data analysis - a significant plus for this role Familiarity with networking concepts (SDN, cloud-native networking, BGP, telemetry) Experience with model evaluation and benchmarking (LLM-as-judge, RAGAS, or custom eval harnesses) Exposure to MCP (Model Context Protocol) for tool-augmented agentic workflows Prior experience in enterprise SaaS, networking, or telecom domains Publications, open-source contributions, or projects in the LLM/GenAI or agentic AI space Our Stack Python PyTorch OpenAI / Anthropic APIs LangChain LangGraph AWS Bedrock AgentCore LangSmith Kubernetes Kafka Elasticsearch AWS PostgreSQL GitHub Jira Confluence.This position is open to all candidates. Hide