AI Systems Engineer - Agents & Inference
Axelera AI3 hours ago
Remote, Spain +12 moreSenior
Responsibilities
- Build reliable agent systems, intelligent tools, and application integrations.
- Develop secure, scalable execution environments for demanding AI workloads.
- Build and maintain Wingman capabilities, including accelerated computing access and remote workload execution.
- Deploy and optimize computer vision models, LLM services, and inference infrastructure to validate the agentic AI platform.
- Own capabilities from implementation and hardware validation through production operation.
- Test functionality, security boundaries, hardware behavior, and failure recovery.
- Write documentation, reproducible setup instructions, and operational runbooks.
- Investigate failures across model code, inference SDKs, and execution environments.
- Collaborate effectively and exercise sound technical judgment.
Requirements
- Practical experience building with AI agents, model APIs, and tools.
- Understanding of agent interactions with applications, state management, and failure recovery.
- Experience with tool calling, structured outputs, streaming, or MCP.
- Understanding of AI workloads across applications, hosts, and accelerated hardware, including remotely hosted environments.
- Comfort working with Linux, processes, resource allocation, and diagnosing failures across the software and compute stack.
- Knowledge of security principles involving permissions, credentials, and workload isolation.
- Ability to build reliable execution with progress tracking, cancellation, and recovery.
- Hands-on experience deploying computer vision models and working with LLM services.
- Ability to validate platform correctness using representative applications and inference workloads on real hardware.
- Ability to assess model accuracy, latency, throughput, and resource use.
- Preferred experience with Python, Rust or another systems language, APIs, databases, native integrations, TypeScript, React, Tauri, workload orchestration, authentication, authorization, sandboxing, cloud operations, PyTorch, ONNX, retrieval, or distributed inference.
- Additional strengths include fine-tuning, multimodal applications, desktop packaging, and maintaining developer tools.
- The company values demonstrated ability and judgment over particular degrees or certifications.
Benefits
- Flexible work arrangement from listed Axelera AI offices or fully remote from any European country, including the UK, where the candidate is already based.
- Attractive compensation package including a pension plan, extensive employee insurances, and the option to receive company shares.
- International, collaborative, inclusive culture with autonomy and responsibility.
Categories
About Axelera AI
Axelera AI builds AI accelerators and an edge inference software stack (the Metis AI Platform) for computer vision and other workloads, selling chips, cards, and developer kits to OEMs and solution providers. Privately held and founded in 2021, it is headquartered in Eindhoven with R&D offices in Belgium, Switzerland, the UK, and Italy. The company focuses on on-device AI deployments where latency, power, and cost are critical.