Senior Full Stack Developer

About Copperhelm

Copperhelm is building the next generation of cloud security, powered by agentic AI. Our platform deploys AI agents that investigate cloud infrastructure vulnerabilities with the depth and judgment of a senior security engineer, mapping downstream impact, filtering out false positives, and delivering prioritized, actionable remediation plans. We are a small, high-velocity team based in Tel Aviv solving one of cybersecurity's hardest problems: turning overwhelming volumes of cloud findings into clear, contextualized action.

About This Role

We are looking for a Senior Backend AI Developer to architect and build the intelligent backbone of our platform: the multi-agent investigation pipeline, the data layer that consolidates signals from cloud providers and security tools, and the orchestration layer that ties it all together. You will work at the intersection of backend engineering and applied AI, designing systems that are durable, scalable, and smart enough to reason about complex cloud security environments.

What You'll Do

• Design and build the backend services that power Copperhelm's AI-driven investigation and remediation engine.
• Architect and evolve a multi-agent system where specialized AI agents collaborate to investigate, prioritize, and resolve cloud security findings autonomously.
• Build and optimize agent workflows using the Claude Agent SDK and Temporal.io for durable, orchestrated execution of long-running investigations.
• Design and maintain the LLM inference pipeline, including prompt engineering, output validation, and integration with Amazon Bedrock.
• Collaborate with product and engineering to translate threat models and investigation playbooks into automated agent workflows.
• Make critical architectural decisions on agent boundaries, coordination patterns, data models, and scaling strategies.
  
  

• 7+ years of professional experience building production backend systems in TypeScript or Python (we use TypeScript / NestJS).
• Hands-on experience designing and integrating AI/LLM-powered features, including prompt engineering, agent frameworks, or RAG patterns.
• Strong understanding of multi-agent system design: agent decomposition, inter-agent communication, tool use, and orchestration patterns.
• Strong proficiency in relational database design (PostgreSQL).
• Experience with cloud infrastructure (AWS, Azure, or GCP) in production environments.
• Experience with workflow orchestration or distributed systems (Temporal.io, Step Functions, or similar durable execution frameworks).
• Proven ability to take full ownership of complex backend systems, from design through production operations.
• A team-player mindset: you communicate clearly, give and receive feedback well, and thrive in a collaborative, fast-paced environment.
  
  

• Experience with cybersecurity, vulnerability management, or cloud security posture management.
• Familiarity with the Anthropic Claude API, Claude Agent SDK, or Amazon Bedrock.
• Background in building multi-agent systems or autonomous AI pipelines in production.
• Experience with Terraform, Kubernetes, or infrastructure-as-code in production environments.
  
  

• Ground-floor opportunity at a funded startup tackling a massive, unsolved problem in cloud security.
• Work at the intersection of AI and cybersecurity, two of the fastest-moving domains in tech.
• High-ownership culture where your work directly shapes the product and the company.
• Modern tech stack with room to influence tooling and architecture decisions.
• Tel Aviv-based team with a bias for speed, quality, and shipping.