Remote Lead Edge AI Engineer

Description:

• Velotio Technologies is looking for a Lead Edge AI Engineer with expertise in GPU/TPU acceleration to join their team.
• The role involves shaping the future Edge AI solution by leveraging GPU/TPU acceleration and large-scale edge compute.
• Responsibilities include designing and optimizing AI inference models for deployment on edge devices, collaborating with cross-functional teams, and staying updated on GPU/TPU technologies.
• The successful candidate will provide technical expertise and support to project teams for the implementation and deployment of edge AI solutions.

Requirements:

• High-Level Design and Architecture experience is required.
• Extensive hands-on experience in AI model development and deployment, focusing on edge computing and local Low Latency Model (LLM) inference.
• Strong programming skills in Python and C++ are necessary.
• Proficiency in LLM frameworks and deep learning libraries is essential.
• Experience with GPU/TPU acceleration for AI inference, including optimization techniques and performance tuning, is a must.
• Knowledge of GPU memory layout, parallel computation, and memory scheduling is required.
• Problem-solving skills, analytical mindset, and a passion for innovation are necessary.

Benefits:

• Velotio offers an autonomous work culture with fast decision-making and a startup-oriented environment.
• The company has a flat hierarchy, encouraging individuals to take ownership and grow quickly.
• A positive work environment with regular celebrations of success is maintained.
• Velotio values diversity and inclusion, welcoming applications from individuals regardless of background.