Staff AI Application Engineer - Heterogeneous Computing
European AI-semiconductor company building AI inference accelerators and software for embedded, edge, server, and data-center deployments.
Funding history
About Axelera AI
Axelera AI develops purpose-built AI acceleration hardware and the Voyager SDK for computer-vision, generative-AI, and other inference workloads, emphasizing power- and thermally-constrained deployments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build model enablement tools and agent workflows for model bring-up. You will own model ingestion and partitioning across accelerators, extend heterogeneous execution for large and multi-model workloads, optimize end-to-end performance, and turn lessons from critical models into platform improvements.
Requirements
- 8+ years of engineering experience in systems, compilers, runtimes or performance
- System-level design ownership
- Heterogeneous computing
- Computer architecture
- Operating systems
- Parallel programming
- ML graph representations
- Compiler concepts
- C++
- Python
- AI coding agent usage
Responsibilities
- Build model enablement platforms, agent harnesses and verification workflows
- Own model capture, analysis and partitioning across AIPUs, CPUs and host accelerators
- Extend heterogeneous execution for large models and multi-model pipelines
- Optimize end-to-end performance across host and device work
- Profile device time, host time and data movement
- Study critical customer models and turn findings into platform improvements
Benefits
- Pension plan
- Employee insurances
- Company share option