Experience: 8yrs
Location: Hyderabad/Bangalore
Job description:
We are seeking a highly skilled and passionate Lead Computer Vision Engineer with expertise in robotics to join our team. As a Lead Engineer you will play a key role in developing and advancing cuttingedge solutions in the field of computer vision and robotics. We are looking for individuals with a strong background in computer science mathematics and machine learning as well as leadership skills to drive innovation
Key Responsibilities:
- Design and implement computer vision algorithms and models to analyze and interpret visual data.
- Develop and optimize image processing pipelines for object detection recognition and tracking.
- Create and train deep learning models for image classification and semantic segmentation.
- Collaborate with crossfunctional teams to integrate computer vision solutions into products and systems.
- You will lead a team of researchers and engineers in the field of computer vision and robotics to deliver innovative products and solutions
- Experiment with stateoftheart methods in object detection scene reconstruction and motion planning
- Train neural networks on inhouse domainspecific datasets
- Analyze experimental results and come up with ways to improve the robustness sample efficiency accuracy and other model properties
- Design and implement domainspecific benchmarks profile and optimize the performance of neural networks as well as endtoend systems
- Design and build robotic applications combining multiple perception and motion planning models
- Enhance datasets for comprehensive training in manipulation and streamline data review cleaning and labelling processes
- Research and evaluate the latest advancements in computer vision and recommend innovative approaches.
- Optimize algorithms for realtime performance and resourceconstrained environments.
- Conduct testing and validation of computer vision systems to ensure accuracy and robustness.
- Contribute to technical documentation including algorithm specifications and performance reports.
- Participate in code reviews and provide mentorship to junior team members.
Required Qualifications:
- Masters or Ph.D. in Computer Science Electrical Engineering or related field.
- Proven experience in computer vision image processing and machine learning.
- Proficiency in programming languages such as Python C or Java.
- Strong background in deep learning frameworks like TensorFlow PyTorch or Keras.
- Solid understanding of 3D computer vision point clouds and spatial transformations.
- Experience with libraries and tools for computer vision development such as OpenCV.
- Solid fundamentals and experience in computer vision (linear algebra object detection structure from motion visionlanguage models)
- Experience in robotics or edge is a big plus: evidence of practical experience and projects that involve scene reconstruction depth estimation calibration or deployment on edge devices
- Experience leading a team of AI/ML engineers
- Published research: particularly around computer vision and robotics demonstrates a deep understanding and contribution to the field
- Ability to work with largescale datasets and implement data augmentation techniques.
- Knowledge of GPU programming for accelerated computation in computer vision tasks.
- Excellent problemsolving skills and analytical thinking for algorithm development.
- Effective communication and collaboration skills to work in multidisciplinary teams.
- Demonstrated ability to deliver highquality productionready code for computer vision applications.
- Experience with version control systems and agile development methodologies.
- Familiarity with cloud platforms and edge computing for deploying computer vision solutions.
- Understanding of image annotation and labeling processes for training supervised learning models.
object detection,vision-language models,computer science,image processing,machine learning,opencv,gpu programming,deep learning,python,agile development methodologies,leadership,computer vision,tensorflow,mathematics,linear algebra,edge computing,version control systems,pytorch,cloud platforms,motion,robotics,structure from motion,3d computer vision,neural networks,datasets