Machine Learning & Computer Vision Engineer

Sentiac; India; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Sentiac is seeking a Machine Learning & Computer Vision Engineer in India to build vision and learning systems for robots using image, video, sensor, and time-series data. You will drive end-to-end experimentation from data collection to model integration.

Responsibilities include developing object detection, segmentation, keypoint and pose estimation, tracking workflows, and multimodal learning. You will review research, establish baselines, and translate papers into actionable experiments for

Qualifications

• Strong Python and PyTorch experience with modern CV/DL architectures.
• Experience with image or video datasets and evaluation metrics.
• Knowledge of detection, segmentation, tracking, pose estimation or action recognition.
• Ability to design controlled experiments and meaningful metrics.
• Experience with Linux and GPU-based model training.
• Ability to translate research papers into working experiments.
• Understanding of data collection, labeling, training, validation, and model integration.

Responsibilities

• Build vision and learning systems for robots using image, video, sensor, and time-series data.
• Develop image and video understanding capabilities.
• Build object detection, segmentation, keypoint detection, pose estimation, and tracking workflows.
• Analyse actions and multi-step processes over time.
• Develop multimodal learning using visual, sensor, and time-series data.
• Build failure detection, confidence estimation, and automated verification capabilities.
• Create data collection, annotation, training, and evaluation pipelines.
• Integrate trained models into larger software systems.
• Review research, establish baselines, compare model families, analyse failures, and recommend a practical technical path.

Skills

Computer vision

Deep learning

Python

PyTorch

Image and video datasets

Experiment design and evaluation

Linux and GPU training

Research paper comprehension

Data labeling and collection

Tools

Python

PyTorch

Job description

Machine Learning & Computer Vision Engineer

Build vision and learning systems for robots using image, video, sensor, and time-series data. Work across data collection, model evaluation, and integration into production software.

• Develop image and video understanding capabilities.
• Build object detection, segmentation, keypoint detection, pose estimation, and tracking workflows.
• Analyse actions and multi-step processes over time.
• Develop multimodal learning using visual, sensor, and time-series data.
• Build failure detection, confidence estimation, and automated verification capabilities.
• Create data collection, annotation, training, and evaluation pipelines.
• Integrate trained models into larger software systems.
• Review research, establish baselines, compare model families, analyse failures, and recommend a practical technical path.

What we are looking for

• Strong Python and PyTorch experience.
• Good understanding of modern computer-vision and deep-learning architectures.
• Experience working with image or video datasets.
• Knowledge of detection, segmentation, tracking, pose estimation, or action recognition.
• Ability to design controlled experiments and define meaningful evaluation metrics.
• Experience with Linux and GPU-based model training.
• Ability to understand research papers and convert them into working experiments.
• Good understanding of data collection, labelling, training, validation, and model integration.

Good to have

• YOLO, RT-DETR, or Mask R-CNN for detection and segmentation.
• ViTPose, Keypoint R-CNN, or ByteTrack for pose estimation and tracking.
• VideoMAE, Video Swin Transformer, or MS-TCN for video and temporal understanding.
• Behaviour Cloning, Action Chunking with Transformers, or Diffusion Policy for learning-based control.
• Experience with multimodal learning, synthetic data, domain adaptation, uncertainty estimation, or robotics-related applications.

Who will fit this role

You should be comfortable owning an experimentation track independently, from understanding the problem and identifying the required data to training models, comparing approaches, and presenting a clear recommendation. You can help decide what should be built, which approaches should be tested, and how to prove that the selected solution works.

A project or technical problem you are proud of