Senior AI/Machine Learning Engineer Python, PyTorch

FinOS Technology is a fintech company with the mission to provide simple, affordable and tech- enable financial products & service thought all digital ecosytem.
Model Development & Optimization

Optimize training and inference pipelines for performance, scalability, and cost efficiency.
Fine- tune and adapt state- of- the- art OCR/document models (Donut) for production use.
Maintain and enhance existing AI models for OCR on Vietnamese ID cards (CCCD) and extend to other document types (passports, driver licenses, bank documents).

Data Pipeline & Quality Management

Build preprocessing and augmentation pipelines: image quality checks, blur/rotation detection, Vietnamese text normalization, PII masking.
Ensure data quality and evaluation consistency across multiple document types.
Manage large datasets combining synthetic and real- world document images.

Accuracy & Performance Evaluation

Define and monitor evaluation metrics: character/word accuracy, exact match rate, edit distance, latency.
Implement image/document quality control to prevent poor inputs from degrading OCR accuracy.
Analyze failed predictions (e.g., accents, truncated fields, misrecognized entities) and integrate findings into retraining cycles.

Production & Monitoring

Investigate and resolve production failures, manage rollbacks, and improve system robustness.
Deploy, monitor, and maintain OCR models serving production workloads (100k+ documents/month).
Collaborate with backend engineers to integrate OCR APIs with downstream systems.

Collaboration & Leadership

Contribute to the long- term roadmap for Document AI, beyond ID cards, to support broader fintech/eKYC and document processing needs.
Document experiments, model updates, and operational practices.
Mentor junior engineers in computer vision and OCR best practices.

Yêu cầu công việc

Must- have

Experience with Vietnamese text processing (accents, tokenization, normalization).
Knowledge of Linux, Docker, and Git.
Experience scaling machine learning services for high traffic.
Experience deploying ML models into production environments.
3+ years of AI/ML engineering experience with Python and PyTorch.
Familiarity with deep learning model training and fine- tuning, preferably with HuggingFace Transformers or OCR frameworks (PaddleOCR, Tesseract).
Practical experience in OCR or Computer Vision (e.g., image preprocessing, OpenCV).

Nice- to- have

Model optimization skills: quantization, distillation, ONNX/TensorRT.
Background in fintech/eKYC or handling sensitive/PII data.
Knowledge of MLOps tools (Weights & Biases, MLflow, DVC).

🌟 Soft Skills

Problem- solving ability: capable of debugging training and inference issues.
Strong ownership mindset: accountable for the full lifecycle of OCR models.
Collaborative attitude: work closely with backend, product, and QA teams.
Communication skills: explain ML concepts and findings to technical and non- technical stakeholders.

⚙️ Tech Stack

Git, DVC (optional)
OpenCV, PIL
MLflow / Weights & Biases (nice- to- have)
Docker, Linux
Python, PyTorch, HuggingFace Transformers, PaddleOCR

Tại sao bạn sẽ yêu thích làm việc tại đây

Provision of work equipment (Macbook/ Laptop, mouse, monitor, etc.).
Competitive salary package (Base salary and performance bonuses).
A creative and modern working environment.
Comprehensive health and accident insurance.
Probation period salary is 100% of the official salary.
15 days of annual leave, 3 days work from home/month.

Cập nhật gần nhất lúc: 2025-11-07 14:55:02