Overview
Overview:
We are seeking a highly skilled Edge AI Engineer to join our growing team. The ideal candidate will have a strong background in computer vision, specifically object detection and classification, and will also be experienced in training and evaluating deep learning models. Additionally, a working knowledge of embedded programming, cross-compilation, and Qt development is a significant plus.
Key Responsibilities
Computer Vision Model Development
- Design, train, and implement object detection and classification models using various state-of-the-art deep learning architectures (e.g., YOLO, Faster R-CNN, SSD, etc.).
- Conduct video classification tasks and integrate them into existing or new systems.
- Experiment with different neural network architectures and algorithms to optimize performance on edge devices.
Model Training & Hyperparameter Tuning
- Set up training pipelines and perform hyperparameter tuning to achieve the best balance between accuracy and efficiency.
- Track model performance, benchmark against baseline and SOTA results, and deliver insights for continuous improvement.
Performance Evaluation & Experimentation
- Compare and benchmark different approaches (e.g., accuracy, speed, resource consumption) to identify the best solution for each use case.
- Use both quantitative and qualitative methods to evaluate model performance and present findings to stakeholders.
Embedded Programming & Edge Deployment
- Develop and optimize AI solutions for deployment on edge devices, ensuring efficient memory usage and real-time inference speeds.
- Use cross-compilation techniques to build and deploy applications on various platforms and hardware environments.
Qt and Application Development
- (Nice to have) Leverage Qt for creating user-friendly interfaces and applications to showcase AI functionality on edge devices.
- Integrate AI modules within Qt-based applications, ensuring seamless communication between the front end and back-end processes.
Collaboration & Documentation
- Work closely with cross-functional teams including software engineers, hardware engineers, and product managers to define requirements and deliver cutting-edge AI solutions.
- Document development processes, model architectures, and results for easy knowledge sharing and project continuity.
Qualifications
Education:
- Bachelor’s or Master’s in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
Technical Expertise:
- Strong experience in computer vision (object detection, classification, video classification).
- Proficiency with deep learning frameworks (e.g., TensorFlow, PyTorch).
- Experience with hyperparameter tuning and model optimization techniques.
- Solid knowledge of C++ or Python, and familiarity with embedded programming.
Embedded & Cross-Compilation Skills:
- Previous experience deploying models on embedded systems (e.g., NVIDIA Jetson, Raspberry Pi, or similar edge devices).
- Understanding of cross-compilation toolchains and performance optimization on hardware-constrained environments.
Software & Tools:
- Familiarity with version control (Git) and CI/CD workflows.
- (Nice to have) Experience with Qt for GUI development and integration.
Soft Skills:
- Strong problem-solving abilities and attention to detail.
- Excellent communication skills and ability to work in a collaborative environment.
- Eagerness to stay updated with the latest AI and embedded systems research.
Job Types: Full-time, Permanent
Pay: ₹300,000.00 - ₹400,000.00 per year
Benefits:
- Flexible schedule
Schedule:
- Day shift
- Fixed shift
- Monday to Friday
- Morning shift
Work Location: In person