Senior AI-Vision Engineer
We are hunting the top Deep Learning Researchers to join our family. We're looking for individuals who are driven to tackle state-of-the-art techno logical obstacles and are passionate about transforming the logistics and trade industry through X-RAY imaging perspective. As part of our team, you will contribute to developing AI-driven software that revolutionizes customs control processes, significantly speeding up cargo x-ray inspections, and improving fraud detection.
________________________________________________________________________________
Job Description
- Research of deep learning models for self-supervised and contrastive learning tasks using SOTA algorithms for X-ray imaging
- Extensive experience working with Large Language Models (LLMs).
- R&D of fusion algorithms for multiple data sources (visual, textual, and numerical data)
- Collaborate with software/data engineers and customs authorities experts
A day in the life
- Tackle complex, real-world customs inspection challenges where no “off-the-shelf” solutions exist
- Build AI systems that accelerate cargo x-ray inspection and uncover fraudulent trade activities—fusing vision, NLP, and structured data
- Research and develop deep learning models for self-supervised learning, contrastive representation learning, and uncertainty quantification
- Design fusion algorithms across multi-modal inputs: X-ray images, scanned documents, textual declarations, and structured numerical data
- Continuously ingest and utilize large-scale international customs datasets and annotated X-ray scans
- Collaborate with a cross-functional team of software engineers, data engineers, and domain experts from customs authorities
- Contribute production-grade code, and work hand-in-hand with engineering teams to deploy research outcomes in live systems
- See the broader system context: develop solutions mindful of performance, scale, integration points, and real-world policy constraints
You bring to the table
- Track record of working on production-grade computer vision and LLM/NLP-based systems
- M.Sc. or Ph.D. in Computer Science, Electrical Engineering, or equivalent STEM field (Deep Learning–focused thesis required)
- 5+ years of industry experience building and shipping deep learning systems, with a strong focus on computer vision
- Hands-on expertise with PyTorc
h and Python's scientific stack (NumPy, Pandas, etc.) - Extensive experience working with Large Language Models (LLMs), including evaluation and deployment in production environments
- Experience with distributed training techniques and handling large-scale datasets
- Strong background in multi-modal AI, including fusion of visual, textual, and numeric data
- Solid understanding of uncertainty modeling and quantification in AI systems
- Bonus: experience in GCP/AWS services, customs/logistics applications
, or multi-view visual reasoning - Excellent coding practices, with a passion for clean, well-structured, and maintainable code
- Team-player mindset with strong analytical thinking and a drive to build systems that matter
Experience & Education
- 8+ years of industry experience building and shipping deep learning systems, with a strong focus on computer vision
- M.Sc. or Ph.D. in Computer Science, Electrical Engineering, or equivalent STEM field (Deep Learning–focused thesis required)
Fully Remote | Full-Time Position
For applications:



