Autonomous Driving: End-to-End Multimodal AI Scientist

Black Sesame Technologies (Singapore) Pte Ltd; Singapore; On-site; SGD 150,000 - 210,000; Full time

Job summary

Black Sesame Technologies (Singapore) Pte Ltd is seeking a research-led engineer to design and develop autonomous driving frameworks that integrate perception, prediction, and planning into a unified system, leveraging vision-only and vision-language modeling to support urban and highway scenarios.

The role emphasizes end-to-end and hybrid architectures, exploring Vision-Language Models to enhance scene understanding, reasoning, and robustness, with hands-on work in model deployment on embedded

Qualifications

• PhD in CS/AI/Robotics or related field.
• Hands-on experience with end-to-end deep learning–based modeling.
• Experience in planning, control, or decision-making modules using DL.
• Interest in Vision-Language Models and multimodal learning.
• Proficiency in C/C++ and Python with real-time deployment.
• Experience with BEV representations and multi-task learning.
• Experience with system integration and real-vehicle testing is a plus.

Responsibilities

• Lead the design and implementation of end-to-end autonomous driving models.
• Develop pure vision-based end-to-end systems with multi-task capabilities.
• Explore Vision-Language Models to improve scene understanding and reasoning.
• Optimize and deploy models on embedded platforms, including deployment and testing.
• Deliver production-ready solutions for highway and urban driving with scalable deployment.

Skills

Deep learning modeling

C/C++

Python

Vision-Language Models

BEV representations

Multi-task learning

Real-time inference

System integration

Education

Ph.D. in CS/AI/Robotics

Job description

Black Sesame Technologies (Singapore) Pte Ltd is seeking a research-led engineer to design and develop autonomous driving frameworks that integrate perception, prediction, and planning into a unified system, leveraging vision-only and vision-language modeling to support urban and highway scenarios.

The role emphasizes end-to-end and hybrid architectures, exploring Vision-Language Models to enhance scene understanding, reasoning, and robustness, with hands-on work in model deployment on embedded