AI Engineer (Gemini and Document AI) for an intelligent automation platform.

Main requirements

· Excellent knowledge of Python, REST API and FastAPI.

· Practical experience in computer Vision and image processing.

· Experience using OpenCV, Pillow, or similar libraries.

· Practical experience with Google Cloud Vision API, Vertex AI Gemini, or similar managed AI services.

· Experience working with Document AI, OCR (Optical text recognition) and structured data extraction.

· Understanding the principles of multimodal large language models (Multimodal LLMs) and JSON-based response generation Schema.

· Experience working with Cloud Storage, BigQuery, and Cloud Run.

· The ability to choose the optimal approach between deterministic image processing algorithms controlled by computer vision services and multimodal AI models, depending on the task at hand.

What you will do

· Develop image analysis processes using Google Cloud Vision API and Gemini on the Vertex AI platform.

· Define rules for evaluating the quality of photos, including blurring, lighting, resolution, composition (cropping), overlap (occlusion), and content compliance with specified requirements.

· Process documents and images using Document AI, OCR (Optical Text recognition) and multimodal AI models.

· Develop services and APIs in Python with deployment to Cloud Run.

· Integrate Cloud Storage, BigQuery, Pub/Sub and Eventarc.

· Implement structured AI responses, confidence scoring, exception handling, and human review processes.

· Create test datasets and evaluate the accuracy of image and document processing.

What we offer

Full-time, official employment
Flexible work format: office, remote or hybrid
Private health insurance
Paid vacation/sick days
Access to internal and external educational platforms
Working equipment
Referral program with a bonus for recommendations from friends and former colleagues