onsite
Applied Scientist - Workforce Safety Data & Tech - Amazon
Software Engineer
Lead the design, training, and deployment of computer vision and machine learning models that enhance workforce safety across global operations, leveraging video, image, and sensor data to detect anomalies, recognize activities, and predict risks.
About the role
Key Responsibilities
- Design, develop, and train state‑of‑the‑art computer vision models for activity recognition, anomaly detection, object detection, and risk prediction using video, image, and sensor streams.
- Collaborate with cross‑functional teams to integrate models into production pipelines on AWS, ensuring scalability, reliability, and low latency for real‑time safety monitoring.
- Conduct rigorous experimentation, A/B testing, and performance evaluation to validate model accuracy and robustness in diverse operational environments.
- Translate research findings into actionable insights for safety teams, providing clear documentation and visualizations of model outputs and impact metrics.
- Stay current with emerging CV and ML techniques, proposing innovative solutions to improve safety outcomes and reduce incident rates.
Requirements
- Ph.D. or Master’s in Computer Science, Electrical Engineering, or related field with strong research background in computer vision or machine learning.
- Proven experience building and deploying deep learning models (e.g., CNNs, RNNs, Transformers) at scale using Python and frameworks such as PyTorch or TensorFlow.
- Hands‑on expertise with AWS services (SageMaker, EC2, S3, Lambda) for model training, inference, and monitoring.
- Strong analytical skills, ability to interpret complex sensor and video data, and communicate findings to non‑technical stakeholders.
- Excellent problem‑solving mindset and a passion for applying science to real‑world safety challenges.
Skills
pythonmachine learningcomputer visiondeep learningaws