Senior AI Application Engineer - LLM & VLM Enablement
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 study, prototype and profile LLM and VLM architectures on Metis and Europa hardware. You will turn model and research results into supported Voyager SDK features, define model-side contracts, integrate serving pipelines, measure quality, and improve model bring-up workflows and GenAI capabilities.
Requirements
- 5+ years of software engineering experience
- At least 2 years of ML inference, ML systems or ML tooling experience
- Transformer inference knowledge
- LLM quantization knowledge
- Python
- PyTorch
- Production software delivery
- AI coding agent usage
- Software design
Responsibilities
- Study, prototype and profile LLM and VLM models on Metis and Europa hardware
- Productize model and ML research results as Voyager SDK features with APIs, tests, documentation and release gates
- Own PyTorch references, quantization, weight mapping and model-side contracts
- Integrate LLM and VLM serving into the Voyager SDK pipeline builder
- Measure accuracy against floating-point references and resolve or explain gaps
- Extend the LLM and VLM bring-up platform with hardware-enabled evaluation workflows
- Recommend Voyager SDK capabilities and model-zoo demonstrations for edge GenAI
Benefits
- Pension plan
- Employee insurances
- Company share option