Senior AI Application Engineer - LLM & VLM Enablement (Fully Remote)

Axelera AI; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Pension

Insurance

Stock options

Job summary

Axelera AI is a deep-tech company advancing the next-generation AI platform from research to production in the United States. The role focuses on studying new LLM/VLM architectures and prototyping them on hardware, turning results into supported SDK features with stable APIs, tests, and documentation.

Daily work centers on Python and PyTorch, with integration of LLM/VLM serving into the pipeline builder, including KV-cache management and multimodal inputs.

Qualifications

• 5+ years of software engineering experience with ML focus.
• Strong Python and PyTorch skills required.
• Experience with AI coding agents and ML tooling.

Responsibilities

• Study new LLM and VLM architectures and prototype them on hardware.
• Productize results into SDK features with stable APIs, tests and docs.
• Integrate LLM/VLM serving into the pipeline builder with KV-cache management and multimodal inputs.

Skills

Python

PyTorch

AI coding agents

Software engineering

Transformer inference

Job description

• Own LLM and VLM support on Metis and Europa AIPUs from study to shipping in the Voyager SDK.
• Combine LLM/VLM knowledge with solid software engineering, using AI coding agents daily.

Key Responsibilities:

• Study new LLM and VLM architectures and prototype them on hardware.
• Productize results into supported SDK features with stable APIs, tests, and documentation.
• Integrate LLM/VLM serving into the pipeline builder with KV-cache management and multimodal inputs.

Qualifications:

• 5+ years of software engineering, with 2+ years on ML inference or tooling.
• Strong Python and PyTorch, plus experience with AI coding agents.
• Knowledge of transformer inference, quantization, and practical design from research code.

What We Offer:

• Attractive compensation with pension, insurances, and company shares.
• An open culture supporting creativity, collaboration, and equal opportunity.

Axelera AI is a deep-tech company creating the next-generation AI platform to advance humanity and improve the world. They have raised $450M, employ 250+ people (60+ PhDs) across 21 countries, and foster an open, innovative, and inclusive culture.