AI Platform Engineer

XM Cyber is a global leader in hybrid cloud security. XM Cyber brings a new approach that uses the attacker’s perspective to find and remediate critical attack paths across on-premises and multi-cloud networks. The XM Cyber platform enables companies to rapidly prioritize and respond to cyber risks affecting their business-sensitive systems.

We are seeking a highly skilled and motivated Backend Engineer with a Generative AI orientation to join our Infra team. We are building a new AI Platform from scratch to standardize AI development methods, ensure excellence and efficiency, and deliver robust, scalable, and compliant AI capabilities across our product line.

This platform will handle cross-team concerns, such as prompt management, model access, data filtering, logging, and monitoring, centrally, so individual teams can focus on their own business-specific logic.

As a Backend Engineer with a Generative AI orientation, you will be instrumental in designing, developing, and implementing the core services of this foundational AI Platform. You will build components that enable our development teams to quickly innovate with AI while adhering to high standards for quality, cost-effectiveness, and compliance.

Responsibilities:

• Develop and maintain a centralized microservice that handles all AI model interactions.
• Build shared services and libraries to maximize development speed and cost-efficiency for AI based features/systems across the company.
• Setting the tone in the fields of automatic testing strategies and CI/CD for AI components, prompt management, and more.
• Define and enforce best practices for model governance, security, and compliance.

Requirements:

• 5+ years of experience as a Backend Engineer or similar role, specifically building and operating production-grade, scaled APIs and microservices.
• Experience with Generative AI concepts and Large Language Models (LLM's).
• Proven self-learner with the ability to quickly grasp new technologies and complex domains.
• Hands-on experience with Kubernetes (K8s) and cloud platforms (AWS, GCP).
• Experience with CI/CD pipelines and integrating automated tests.
• Proven ability to solve complex technical problems and make data-driven decisions.
• Excellent communication and collaboration skills, with a track record of working effectively in a team-oriented environment.
• Hands-on experience with observability tools such as Prometheus, Open Telemetry etc.

Bonus Points:

• Familiarity with Go programming language.
• Experience working within an Infrastructure or Core Engineering team.
• Experience with LLM orchestration frameworks like Lang Chain.
• Familiarity with prompt engineering, prompt optimization techniques, and managing system prompts.