Test d'automatisation pour Scanpoint SoftwareJob Title: Lead Data Scientist & Computer Vision Engineer – Animal AI Analysis (4-Month full time Project)
Budget: ₹750 – ₹1,250 INR
Project Overview: Equi-Vision AI :
Equi-Vision AI is an ambitious R&D project dedicated to revolutionizing Show Jumping (CSO) analysis. We are developing a cutting-edge engine to automate equine biomechanical and behavioral evaluation through advanced Computer Vision. Our goal is to extract high-precision metrics (articulation angles, jump trajectories, behavioral signals) from non-standardized competition videos.
Your Mission
As the Lead Data Scientist, you will be the architect of our core AI engine. Your role is to implement a high-performance multi-level pipeline that translates raw video frames into structured athletic and psychological data.
Core Responsibilities
Detection & Tracking: Implement and fine-tune state-of-the-art models (YOLO11 or RT-DETRv2) coupled with robust trackers (ByteTrack / BoT-SORT) for horse/rider/obstacle isolation.
Pose Estimation: Deploy and optimize animal pose estimation frameworks (DeepLabCut, SuperAnimal, hSMAL) to track 100+ equine keypoints with sub-pixel precision.
Temporal Analysis: Develop spatio-temporal understanding of the jump phases (Approach, Take-off, Flight, Landing) using VideoMAE or TimeSformer.
Data Correlation: Translate biomechanical outputs into performance scores and predictive potential markers.
Required Technical Stack
Languages/Frameworks: Python, PyTorch (Advanced).
Vision: YOLO v8-v11, RT-DETR, Ultralytics, DeepLabCut, SLEAP.
Spatio-Temporal: VideoMAE, Video Swin Transformer, TimeSformer.
Deployment/Optimization: ONNX Runtime, TensorRT, MLOps (Weights & Biases / MLflow).
Mandatory Candidate Qualifications
We are looking for a top-tier expert. Please only apply if you meet the following criteria:
Serious References: You must provide verifiable case studies or GitHub repositories of similar complex computer vision projects (pose estimation, motion analysis, or animal tracking).
Experience: At least 5+ years of experience in Computer Vision and Deep Learning.
Accuracy Obsession: Proven ability to deliver high-precision results in environments with moving cameras and varying light conditions.
Animal Biomechanics: Prior experience in equine or animal research is a massive plus.
Project Terms
Duration: 120 days (Full-time or high-availability part-time over 6 months).
Daily Rate (TJM): up to 40€/ day for real experimented profiles
Type: Remote / Freelance contract.
How to Apply
To apply, please provide:
A brief summary of your most relevant project in Animal Pose Estimation or Biometrics.
A link to your portfolio, GitHub, or published research papers.
Your availability to start.
Note: Applications without serious production-level references will not be considered.
Equi-Vision AI is an ambitious R&D project dedicated to revolutionizing Show Jumping (CSO) analysis. We are developing a cutting-edge engine to automate equine biomechanical and behavioral evaluation through advanced Computer Vision. Our goal is to extract high-precision metrics (articulation angles, jump trajectories, behavioral signals) from non-standardized competition videos.
Your Mission
As the Lead Data Scientist, you will be the architect of our core AI engine. Your role is to implement a high-performance multi-level pipeline that translates raw video frames into structured athletic and psychological data.
Core Responsibilities
Detection & Tracking: Implement and fine-tune state-of-the-art models (YOLO11 or RT-DETRv2) coupled with robust trackers (ByteTrack / BoT-SORT) for horse/rider/obstacle isolation.
Pose Estimation: Deploy and optimize animal pose estimation frameworks (DeepLabCut, SuperAnimal, hSMAL) to track 100+ equine keypoints with sub-pixel precision.
Temporal Analysis: Develop spatio-temporal understanding of the jump phases (Approach, Take-off, Flight, Landing) using VideoMAE or TimeSformer.
Data Correlation: Translate biomechanical outputs into performance scores and predictive potential markers.
Required Technical Stack
Languages/Frameworks: Python, PyTorch (Advanced).
Vision: YOLO v8-v11, RT-DETR, Ultralytics, DeepLabCut, SLEAP.
Spatio-Temporal: VideoMAE, Video Swin Transformer, TimeSformer.
Deployment/Optimization: ONNX Runtime, TensorRT, MLOps (Weights & Biases / MLflow).
Mandatory Candidate Qualifications
We are looking for a top-tier expert. Please only apply if you meet the following criteria:
Serious References: You must provide verifiable case studies or GitHub repositories of similar complex computer vision projects (pose estimation, motion analysis, or animal tracking).
Experience: At least 5+ years of experience in Computer Vision and Deep Learning.
Accuracy Obsession: Proven ability to deliver high-precision results in environments with moving cameras and varying light conditions.
Animal Biomechanics: Prior experience in equine or animal research is a massive plus.
Project Terms
Duration: 120 days (Full-time or high-availability part-time over 6 months).
Daily Rate (TJM): up to 40€/ day for real experimented profiles
Type: Remote / Freelance contract.
How to Apply
To apply, please provide:
A brief summary of your most relevant project in Animal Pose Estimation or Biometrics.
A link to your portfolio, GitHub, or published research papers.
Your availability to start.
Note: Applications without serious production-level references will not be considered.