Agentic AI Engineer - Product Support

The role

You will design and ship real AI systems to improve support workflows and processes. You will build custom agent-based AI workflows, LLM-powered tools, and RAG pipelines.

What you will do

• Partner with business teams to identify automation and optimization opportunities
• Design and implement agent-based AI workflows to automate internal processes end-to-end
• Design and build LLM-powered tools using frameworks like LangGraph / LangChain
• Develop RAG pipelines, integrate multiple data sources, and build intelligent automation flows
• Validate company data quality and uncover gaps
• Take solutions from idea to prototype to production
• Ensure AI workflows comply with security, privacy, and compliance requirements
• Implement guardrails, approvals, logging, and human-in-the-loop mechanisms
• Monitor AI performance, errors, hallucinations, and drift
• Translate business requirements into AI-driven solutions

Required qualifications

• 3 years of hands-on software development experience, including writing, maintaining, and delivering production-quality code
• 2+ years of GenAI development experience, with strong AI/ML focus
• Strong Python skills and production mindset
• Hands-on and deep understanding with LLMs, SLMs, prompt engineering, context engineering and agent-based systems
• Experience with LangGraph, crewAI, Strands or similar orchestration frameworks
• Experience in enterprise grade agentic solutions and bringing Agents into production
• Solid understanding of ML workflows and MLOps principles
• Strong analytical skills and ability to work directly with non-technical stakeholders
• Builder mindset: proactive, independent, and impact-driven

Nice to have

• Experience in AWS Agent Core
• Experience with Agentic AI driven applications like n8n, UiPath, Make
• Experience or familiarity with the Support domain

About the company

Cato Networks is the converged network and security cloud for the AI era. The company provides a unified, cloud-native platform to prioritize risks and stop threats across users, applications, data, and AI agents.