Sr. AI/ML Engineer - Computer Vision

Opportunity Description: Senior AI/ML Computer Vision Engineer - Tech Lead

At Jinn Labs, we’re reimagining how retail security works—using cutting-edge Vision AI to stop theft before it happens. Our mission? Solve the $100B shrinkage problem in retail with AI-native agents that detect, understand, and act—starting with the most expensive and overlooked issue: employee theft.

Who should consider this opportunity?

We’re looking for candidates who geek out on every stage of the computer-vision pipeline: whether you’re wrangling raw pixels into meaningful features, architecting and running experiments to validate new models, or building bullet-proof data-cleaning pipelines that tame messy, real-world footage. You’ll apply applied statistics at scale—A/B testing architectures, tuning hyperparameters against principled metrics, and interpreting confidence intervals—to drive measurable gains in detection and re-identification accuracy. If you love transforming noise into insight and seeing your algorithms deployed in live retail settings—where each increment in performance directly reduces shrinkage and elevates the customer experience

n this role, you’ll also take the helm in shaping the vision and design of our solutions: defining the core problem statements, mapping out end-to-end data flows, and translating business goals into actionable technical roadmaps. You’ll guide cross-functional teams on experiment design, set success criteria, and prioritize features based on impact and feasibility. Your ability to frame complex challenges, sketch out robust evaluation plans, and push stakeholders toward clear, data-driven decisions will be critical to fast-tracking our path from prototype to production.

What We’re Building:

Our real-time system integrates seamlessly with existing cameras and POS setups in convenience stores, gas stations, and small-format retail. No human monitoring. Just actionable insights, automated responses, and a measurable impact on the bottom line.

Why Jinn?

We’re backed by the Allen Institute for AI (AI2) and have a team with over 100 years of experience across computer vision, ML, and production engineering. Our founders and advisors have driven growth at Amazon, Microsoft, LinkedIn, Rippling, and more. We’ve already helped our first customers unlock major ROI—and we’re just getting started.

Why Now?

We’re well-funded, on the path to raise our seed round, and scaling fast. Joining us now means shaping the core product, influencing the roadmap, and building a system that will be in thousands of stores in the next year.

What You’ll Do:

• Build CV models that run reliably in the wild—across edge devices and cloud pipelines
• Work with a world-class team obsessed with scientific rigor and product impact
• Tackle challenges across detection, tracking, multi-modal fusion, and real-time inference
• Own your work, end-to-end—from research to production

We’d Love to Meet You If:

• You’ve shipped ML/CV models in production (bonus if it’s on the edge)
• You’re excited by real-world messiness and solving hard technical problems
• You want your work to matter—measurably—to customers, not just metrics
• You’re ready to grow fast with a startup that’s moving even faster

(More details below)

Role Description

The Senior Computer Vision Engineer will be responsible for developing and implementing advanced computer vision algorithms, pattern recognition models, on cloud and on the edge computing to improve retail security and operational efficiency.

Key Responsibilities

• Lead the design, development, training, and deployment of state-of-the-art computer vision and machine learning models for real-time applications in retail environments.
• Develop and optimize algorithms for tasks such as:
• Real-time object detection, tracking (people, products), and re-identification.
• Action recognition and behavior analysis for identifying theft-related activities and operational inefficiencies.
• Anomaly detection in video feeds and integrated POS data.
• Architect and implement robust MLOps pipelines for model versioning, training, deployment, monitoring, and continuous improvement on both edge devices and cloud platforms.
• Optimize model performance (latency, throughput, accuracy) for deployment on edge devices with limited computational resources
• Collaborate closely with software engineers to integrate CV models into the broader product architecture and ensure seamless data flow from existing camera infrastructure and POS systems.
• Work with large-scale, real-world video datasets, including developing strategies for data acquisition, augmentation, annotation, and quality control.
• Mentor junior engineers and contribute to a culture of technical excellence and innovation.
• Contribute to system-level design and decision-making regarding our vision pipeline and overall AI capabilities.

Required qualifications

• 5+ years of hands-on experience in developing and deploying computer vision and machine learning models in production environments.
• Deep understanding and practical experience with PyTorch, NumPy; strong proficiency with CUDA for GPU acceleration.
• Ability to work with different model architectures including transformers, CNN and LSTM.
• Demonstrable experience processing and analyzing multiple concurrent video feeds in real-time, with deployments on edge devices and/or cloud platforms.
• Expert programming skills in Python; proficiency in C++ is a strong plus for performance-critical components.
•  Strong theoretical understanding and practical application of Computer Vision techniques (e.g., image processing, feature extraction, multi-view geometry) and Pattern Recognition.
• Extensive experience in the end-to-end lifecycle of AI vision models, including data collection, labeling and annotations, training from scratch, fine-tuning, evaluation, and deployment.
• Strong analytical and problem-solving skills

Preferred qualifications

• Master's or Ph.D. in Computer Science, with a specialization in Computer Vision or Machine Learning.
• Knowledge of at least one cloud provider stack (GCP preferred)
• Experience with quantization, pruning, knowledge distillation, TensorRT, ONNX
• Experience with edge computing platforms and SDKs (e.g., NVIDIA Jetson, DeepStream SDK, Hailo, Raspberry Pi).
• * Understanding of challenges specific to retail environments (e.g., varying lighting conditions, occlusions, camera angles, low-resolution footage)

Send your cover letter and resume to Hr@jinnlabs.ai for consideration.