About the Role :

We are building advanced machine learning solutions to automate image recognition using image processing algorithms, vision-language models, and modern microservices architecture. We are seeking a technically strong engineer who can work across backend systems, AI integration layers, and data pipelines to enable an end-to-end user workflow. This role focuses on building scalable systems that integrate AI and VLM capabilities with microservices architecture to enable automated planogram generation from shelf images.

Responsibilities :

- Build and enhance microservices for computer vision models, image recognition, image processing pipelines, and AI model integration.

- Integrate computer vision and VLM services into backend workflows to enable image capture, image decomposition, and image recognition.

- Implement new features using OCR, embedding models, and image training.

- Develop and integrate services for image ingestion and AI/VLM model inference.

- Identify, analyze, and resolve performance bottlenecks and security vulnerabilities.

- Collaborate with global teams across time zones.

- Work independently with strong analytical and problem-solving skills.

Requirements :

- Expertise in image recognition models.

- Expertise in image processing pipelines.

- Experience with AI/ML model integration via APIs.

- Strong experience with Python.

- Experience with API frameworks such as FastAPI or Flask.

- Experience with PyTorch and other image processing packages.

- Strong SQL skills.

- Experience in data modeling.

- Ability to handle large retail datasets.

- Experience using LLMs for business rule translation and scenario simulation.

- Prompt engineering experience for structured outputs.

- Strong understanding of microservices architecture and API-driven workflows.

- Experience integrating with upstream VLM systems and downstream UI or application systems.

- Ability to work with AI teams and productionize ML outputs.

- Good To Have : Retail domain knowledge.