Autonomous Robotic Vision-Language Engineer

AsiaCruit, Inc.; Town of Delhi (NY); Sur place; USD 120 000 - 180 000; Plein temps

Résumé du poste

AsiaCruit, Inc. is seeking a Multimodal AI Engineer to develop Vision-Language-Action foundation models for autonomous robotic systems. You will fine-tune multimodal models, build multi-camera perception pipelines, and optimize for edge deployment, collaborating with AI researchers and robotics engineers to turn research into practical, high-performance AI capabilities.

The role emphasizes transformer-based architectures, PEFT (LoRA), and scalable inference using NVIDIA TensorRT.

Qualifications

• Master's degree or Ph.D. in Computer Science, AI, Robotics, ML, CV, or related field.
• 3–5 years of relevant multimodal AI, deep learning, or robotic learning experience.
• Strong Python programming and PyTorch hands-on experience.
• Experience with Transformer-based architectures and vision-language models.
• Familiarity with PEFT methods (LoRA) and edge deployment concepts.
• Knowledge of multi-camera perception, fusion, and downstream planning.

Responsabilités

• Develop, fine-tune, and adapt ViTs and multimodal foundation models for robotic perception and action generation.
• Build multi-camera fusion pipelines for VLA perception and decision-making.
• Implement action-chunking architectures (ACT, Diffusion Policy) for long-horizon planning.
• Optimize multimodal feature extraction for planning and execution systems.
• Prepare model weights for deployment using TensorRT and related tools.
• Collaborate with researchers and engineers across VLA and robotics teams.

Connaissances

Python

PyTorch

Vision Transformers

PEFT LoRA

Multimodal AI

Robotics

Formation

Master's or PhD in CS/AI/Robotics

Outils

NVIDIA TensorRT

NVIDIA DeepStream

Vector search

Description du poste

AsiaCruit, Inc. is seeking a Multimodal AI Engineer to develop Vision-Language-Action foundation models for autonomous robotic systems. You will fine-tune multimodal models, build multi-camera perception pipelines, and optimize for edge deployment, collaborating with AI researchers and robotics engineers to turn research into practical, high-performance AI capabilities.

The role emphasizes transformer-based architectures, PEFT (LoRA), and scalable inference using NVIDIA TensorRT.