Join Haldorix, a startup studio turning real-world operational challenges into scalable business opportunities through technology. We identify recurring problems in industries such as manufacturing, retail, and logistics, and transform them into ventures with measurable impact. We’re looking for a Computer vision/Machine Learning Engineer – Inference & Model Deployment to join our industrial vision venture. You’ll play a key role in developing a real-time computer vision system for monitoring productivity in textile production lines.

- Optimization & Deployment: Export and optimize deep learning models using ONNX and TensorRT (INT8, FP16) for efficient inference on GPU. - Active Learning Loop: Manage data collection, annotation, and correction pipelines within CVAT to continuously improve model performance. - Performance Benchmarking: Conduct GPU stress tests and benchmark latency, throughput, and accuracy across deployment environments. - Validation & QA: Lead field validation sessions, perform detailed QA checks, and ensure robustness in real-time production conditions. - Automation & Scalability: Develop scripts and tools to streamline model conversion, quantization, and deployment workflows. - Collaboration & Documentation: Work closely with CV and backend engineers to integrate optimized inference pipelines and document performance metrics. - Continuous Improvement: Analyze bottlenecks, propose optimizations, and refine the active learning feedback loop for model accuracy. - Testing Culture: Contribute to building a strong testing and profiling culture around ML models in production.

You’ll be part of a small, agile engineering team dedicated to building intelligent vision systems for industrial environments. Working alongside computer vision specialists, data engineers, and QA professionals, you’ll report directly to the Technical Lead overseeing system integration and infrastructure. Collaboration, iteration, and precision define our team culture. Every member is both an engineer and a problem solver focused on creating tangible field impact.

Required: - 2+ years of hands-on experience in ML model deployment and inference optimization - Strong expertise with TensorRT, ONNX, and GPU performance optimization - Experience with quantization techniques (INT8, FP16) - Proficiency in Python for scientific computing and QA/testing workflows - Familiarity with video annotation tools like CVAT or Label Studio - Proven ability to conduct GPU benchmarking and profiling - Strong attention to detail and commitment to production-grade quality Nice to Have: - Experience in industrial computer vision or real-time systems - Familiarity with Active Learning workflows and auto-annotation techniques - Knowledge of Docker or Kubernetes for ML model deployment - Understanding of CI/CD for ML pipelines - Previous experience in manufacturing, logistics, or IoT environments

- Join a startup studio building high-impact industrial ventures from the ground up - Work on cutting-edge real-time computer vision systems deployed in production - Collaborate with a skilled, multidisciplinary team driven by innovation - Gain deep expertise in model optimization and production ML