#vacancy #job #работа #hiring #ComputerVision #cv **👩🏼‍💼 Position: Computer Vision Engineer / Data Scientist 🎓 Level: Senior 💪 Experience: 6+ years (NOT freelance) 🛠 Stack: **CV, SSL, Python, PyTorch, TensorFlow **🌎 Location: **#Remote / #удаленно 🕗 Employment: #Fulltime / #полная 🌐 Timezone: UTC+3 🚀 Company: ITM 💰 Salary: 250,000₽ – 400,000₽ net

🏅 REQUIREMENTS:

1. 6+ years of experience in Computer Vision.
2. Proven experience bringing models to production is mandatory.
3. 1+ year of experience with medical images in production: CT scans, mammography.
4. 3+ years of experience with images in production.
5. 1+ year of experience with document processing / OCR / KYC.
6. 1+ year of experience with biometrics (face, palm, voice, etc.).
7. 1+ year of experience with multimodal models / LLM.
8. 1+ year of experience with Self-Supervised / Weakly-Supervised Learning.
9. 1+ year of experience with fraud detection.
10. 1+ year of experience with 3D data (volumes, point clouds, meshes).
11. 1+ year of experience with video.

🎯 WHO WE ARE LOOKING FOR:

1. Full-time only, no side jobs.
2. We need "hands-on" doers, NOT technical managers.
3. We need someone who has already built complex CV systems, not someone who is learning on the job.

💪 WE EXPECT:

1. Independence.
2. High work speed.
3. Ability to quickly test hypotheses.

⛔️ WHO IS NOT A GOOD FIT:

1. Candidates with predominantly or recent experience as technical managers – this experience is irrelevant to this position. We are looking for "hands-on" doers, not technical managers.
2. Candidates looking for a second job. Any side job will be noticeable within the first 2 months. We need an honest full-time commitment.
3. Candidates with predominantly or recent freelance experience.

🧑‍💻 TASKS: ** Development and improvement of KYC pipelines:**

1. document image processing
2. validation, classification, data extraction
3. detection of fraud scenarios (screen, copies, editing, etc.)

Working with multimodal models: 4. integration of CV and LLM (Vision-Language) 5. model tuning, fine-tuning, and optimization 6. building agent-based systems around LLMs

Development of CV models: 7. detection, segmentation, classification 8. working with documents, images, video

Development of biometric solutions: 9. face matching 10. palm vein / PalmPay

Building and optimizing ML pipelines: 11. training, inference, validation 12. working with large datasets

Participation in R&D: 13. experiment design 14. rapid hypothesis iterations

**✏️ TG: **Tany_Jobs