Stellenbeschreibung:

JupiterOne is a cyber asset attack surface management (CAASM) platform company providing visibility and security into your entire cyber asset universe. Using graphs and relationships, JupiterOne provides a contextual knowledge base for an organization's cyber asset operations. With JupiterOne, teams can discover, monitor, understand, and act on changes in their digital environments.

We're launching Juno, an AI-powered security coworker that transforms our vast asset graph into actionable insights through natural conversation. JUNO goes beyond traditional chatbots—it takes ownership of security outcomes, from investigation to resolution.

As a Lead AI Engineer, you will architect and build the core AI systems that power our next-generation agentic security platform. You'll be responsible for designing scalable AI infrastructure that can process millions of assets and billions of relationships while delivering sub-2-second response times to users.

What You'll Do

• Design and implement agentic AI architectures using frameworks like LangGraph, CrewAI, or similar multi-agent orchestration platforms
• Build graph-aware AI systems that leverage JupiterOne's knowledge graph for context-aware reasoning and decision making
• Implement advanced RAG pipelines that intelligently traverse graph relationships to provide contextual security insights
• Integrate Model Context Protocols (MCPs) to enable seamless AI-to-system communication
• Develop intelligent query translation engines that convert natural language to complex graph queries
• Build workflow automation systems that can execute multi-step security remediation tasks
• Design API layers that enable seamless integration between AI agents and external security tools
• Implement event-driven architectures for real-time security monitoring and response
• Ensure lightning fast response times for AI-powered conversations across millions of assets
• Design fault-tolerant systems with 99.9% uptime SLA for production AI workloads
• Implement comprehensive monitoring and observability for AI system performance and accuracy
• Build auto-scaling infrastructure that handles variable AI workloads efficiently

Requirements

Who You Are:

• 2+ years working with large language models (OpenAI, Anthropic, open-source) in production
• 4+ years building and deploying AI/ML systems in production environments
• Deep experience with agentic AI frameworks (LangGraph, CrewAI, AutoGen) and multi-agent orchestration
• Hands-on experience with RAG architectures, vector databases, and embedding systems
• Strong understanding of graph databases (e.g. Neo4j) and graph query languages (Cypher)
• Experience building AI systems that reason over graph data and complex relationships
• Knowledge of graph algorithms and how to apply them in AI contexts
• Experience with high-volume data processing and distributed systems
• Expert-level system design skills for building scalable, distributed AI applications
• Experience with cloud infrastructure (AWS, GCP, Azure) and containerization (Docker, Kubernetes)
• Strong background in API design and building robust, well-documented interfaces
• Experience with streaming data systems (Kafka, Kinesis) and event-driven architectures
• Proficiency in Python and modern AI/ML libraries (LangChain, LlamaIndex, Transformers)
• Strong TypeScript/JavaScript skills for full-stack AI application development
• Experience with infrastructure as code (Terraform, CloudFormation) and CI/CD pipelines
• Knowledge of software architecture patterns and design principles
  

A Plus To Have:

• Background in cybersecurity, threat modeling, or infrastructure security
• Experience with security data formats and threat intelligence feeds
• Understanding of compliance frameworks (SOC2, ISO, HIPAA) and security controls
• Experience with monte-carlo simulations and building models for risk quantification
• Experience with fine-tuning and optimizing LLMs for domain-specific tasks
• Knowledge of prompt engineering and advanced LLM techniques
• Familiarity with AI safety and alignment best practices
• Experience with model evaluation and monitoring in production
• Experience leading technical teams and mentoring engineers
• Track record of shipping AI-powered products from conception to production
• Strong communication skills for explaining complex AI systems to diverse stakeholders

Benefits

• Medical, Dental, Vision Insurance etc.
• Flexible PTO
• Maternity & Paternity Paid Leave
• Reimbursement for Gym Memberships and/or Fitness Equipment
• Wellness Program Offerings
• 401(k), Life Insurance, Short and Long Term Disability
• Paid Holidays, including JupiterOne Day on July 21st.
• Generous Employee Referral Program
• & SO much more!

NOTE / HINWEIS:

EN: Please refer to Fuchsjobs for the source of your application

DE: Bitte erwähne Fuchsjobs, als Quelle Deiner Bewerbung