Derq is an MIT spinoff building AI-powered traffic safety and smart infrastructure. We’re a team of passionate innovators, leveraging the latest in AI and technology to transform the future of mobility. Our platform enhances road safety and traffic management by turning real-time data into actionable insights for cities and road operators. Our patented technology collects and analyzes data from connected sensors like cameras, radar, and traffic signal controllers to help predict and prevent road incidents. We deploy edge and cloud solutions that make intersections and highways safer and smarter.
Role Overview
We are seeking a motivated Associate Machine Learning Engineer to join our team and contribute to building intelligent, data-driven solutions for real-world traffic and mobility challenges. You will work closely with a multidisciplinary team to design, develop, and deploy machine learning and computer vision systems using diverse sensor data from vehicles and road infrastructure.
Key Responsibilities
Develop cutting-edge machine learning and deep learning solutions using multimodal sensor data from vehicles and road environments.
Design and build scalable software pipelines for computer vision applications, including:
Data curation and preprocessing
Model training and evaluation
Testing and validation
Deployment and monitoring
Create innovative solutions for complex traffic and mobility-related problems.
Design and implement efficient, low-cost approaches for video-based inference.
Train, fine-tune, and optimize machine learning and deep learning models for real-world performance and scalability.
Collaborate with cross-functional teams to contribute to the development of advanced, production-ready systems.
Stay up to date with emerging technologies, research, and open-source tools, and apply them to improve system performance and capabilities. Requirements
Bachelor’s or Master’s degree in Computer Science or a related field.
2+ years of relevant experience in Machine Learning or Computer Vision.
Strong understanding of machine learning and deep learning fundamentals.
Experience with training and optimizing deep learning models, designing loss functions and hyper parameter tuning on real data.
Solid foundation in mathematics including probability and statistics and linear algebra.
Strong knowledge of data structures and algorithms.
Proficiency in Python and C/C++.
Experience writing modular, efficient, and testable code for production systems.
Identify, leverage and develop expertise in emerging technologies, open source tools, and harness new techniques.
