AI Systems Engineer for Agents and Inference

Skills

About the Role

You will build agent capabilities, execution environments and software integrations. You will deploy and optimize models and inference workloads, validate hardware and platform behavior, investigate failures, maintain reliable operations, and create clear setup and operational documentation.

Requirements

• Experience building with AI agents, model APIs and tools.
• Understanding of agent state management and failure recovery.
• Ability to use coding agents while retaining ownership of technical decisions.
• Experience with tool calling, structured outputs, streaming or MCP.
• Knowledge of AI workloads across applications, hosts and accelerated hardware.
• Linux, process, resource-allocation and software-stack troubleshooting experience.
• Knowledge of permissions, credentials and workload isolation.
• Experience deploying computer-vision models and LLM services.
• Ability to assess accuracy, latency, throughput and resource use.

Responsibilities

• Build agent systems, intelligent tools and application integrations.
• Develop secure and scalable execution environments for AI workloads.
• Build and maintain accelerated-computing access and remote workload execution capabilities.
• Deploy and optimize computer-vision models, LLM services and inference infrastructure.
• Own implementation, hardware validation and production operation.
• Test functionality, security boundaries, hardware behavior and failure recovery.
• Write documentation, reproducible setup instructions and operational runbooks.
• Investigate failures across models, inference SDKs and execution environments.

Benefits

• Pension plan.
• Employee insurances.
• Option to receive company shares.