Senior MLOps Engineer - Computer Vision

March 12

Apply Now

Receive Emails with Similar Jobs

HR POD - Hiring Talent Globally

WebsiteLinkedInAll Job Openings

HR POD is a leading premium global recruitment agency dedicated to elevating human resource management services. With a focus on helping companies strategize and build robust HR frameworks, HR POD specializes in recruitment, training, and performance management. They pride themselves on serving a diverse client base, particularly in the tech industry, and adopt a data-driven approach to optimize HR practices that align with organizational goals. Their commitment to integrity, customer satisfaction, and excellence positions them as a reliable partner in enhancing talent acquisition and retention strategies for businesses worldwide.

Staffing • Technical Recruitment • Executive Recruitment • Headhunting • International Recruitment

11 - 50 employees

Founded 2023

👥 HR Tech

🎯 Recruitment

🤝 B2B

📋 Description

• Deploy trained deep learning models using FastAPI, ensuring efficient and scalable inference services. • Optimize machine learning models to reduce inference time, leveraging techniques such as quantization and hardware acceleration. • Develop and maintain Dockerfiles to containerize models, ensuring reproducibility and ease of deployment. • Handle image preprocessing pipelines using OpenCV, PIL, or other image processing libraries to ensure optimal input data quality. • Monitor model performance in production for errors and implement maintenance updates. • Collaborate with backend engineers to integrate models into the existing infrastructure.

🎯 Requirements

• 2+ years of experience in Computer Vision and MLOps. • Master's or Ph.D. in Computer Science, Machine Learning, or a related field. • Hands-on experience with FastAPI and asynchronous programming. • Strong understanding of model optimization techniques. • Expertise in Docker, containerization, and dependency management. • Knowledge of CI/CD pipelines for ML model deployment. • Excellent problem-solving skills and ability to work independently. • Experience with Kubernetes, AWS/GCP/Azure, and serverless deployments. • Familiarity with monitoring tools like Prometheus, Grafana, or the ELK stack. • Familiarity with edge deployment frameworks like TensorFlow Lite, ONNX Runtime, or NVIDIA Triton.