Who We Are:
We are a rapidly growing embodied AI company revolutionizing human labor. Leveraging cutting-edge robotics and advanced artificial intelligence, we develop transformative technologies that redefine how work is done across multiple industries—empowering businesses to streamline operations, boost productivity, and unlock new possibilities.
Overview:
As a Deep Learning Deployment and Optimization Specialist, you will focus on deploying and fine-tuning Deep Learning and Vision Language Action Models (VLAMs) for production use cases. You’ll optimize model performance and collaborate with teams to implement robust deployment strategies.
Your Responsibilities:
Deploy and Optimize
-
Deploy VLAMs in production environments.
-
Optimize model inference and latency.
-
Collaborate on model quantization and compression techniques.
-
Monitor and maintain deployed systems for performance and reliability.
Qualifications:
Education and Experience
-
Bachelor’s or Master’s degree in AI, Data Engineering, or related fields
-
Experience working with VLMs (VIsual Language Model) and Imitation Learning Policies
Skills
-
Expertise in deploying AI models with Python and PyTorch
-
Strong knowledge of Huggingface and Deepspeed frameworks
-
Experience in model optimization techniques and programming with CUDA
-
Proficiency in converting researched models into optimal format such as TensorRT, ONNX, GGUF
-
Strong knowledge of LLM serving framework such as vLLM, SGLang, LMDeploy
What We Offer:
-
Wellpass (gym membership)
-
Free meals at the workplace
-
Flexible working hours
-
Option to work from home when needed
-
A motivated team and an open corporate culture
-
Competitive compensation and excellent career development opportunities
Your benefits
-
Wellpass
-
Flexible working
-
Dynamic team
-
Team events
-
Creative work
#J-18808-Ljbffr
Kontaktperson:
Sereact HR Team