MLOps Engineer, Optimization

About Precision AI

Precision AI is on a mission to transform agriculture with cutting-edge drone technology. Our aerial spraying systems help farmers target weeds with surgical precision, reducing chemical use and increasing yields. We’re a fast-moving, impact-driven team looking for people who want to help build the future of farming.

Role Overview

The MLOps Engineer, Optimization at Precision AI will be responsible for optimizing and operationalizing our machine learning models for efficient deployment on edge devices. This role focuses on using state-of-the-art techniques to accelerate models, automate deployment pipelines, and ensure reliability and scalability in production environments.

You will work closely with our AI/ML, Robotics, and Embedded Systems teams to deliver robust, high-performance ML solutions optimized for UAV-based agricultural applications.

This role is hybrid working out of our Calgary office due to the hands-on nature of drone testing and system integration.

Key Responsibilities

Model Acceleration & Optimization

• Optimize and compile AI models for edge devices (e.g., Jetson Orin) and mobile platforms, focusing on latency, throughput, and memory efficiency.
• Compile and build models for target platforms using toolchains such as NVIDIA TensorRT, ONNX Runtime, TVM, or equivalent frameworks.
• Apply quantization, pruning, and low-level C++ optimizations to improve runtime performance.
• Profile, benchmark, and troubleshoot performance bottlenecks for minimal footprint and reduced load times on embedded systems.

Model Deployment & Scaling

• Automate the deployment of ML models to production environments and APIs.
• Ensure models scale efficiently using container orchestration (e.g., Kubernetes) for both training and deployment.
• Maintain and monitor model hosts for stability and performance.

Reliability, Testing & Monitoring

• Build robust error handling, logging (e.g., CloudWatch), and automated model library updates.
• Add unit, integration, and regression tests to ensure pipeline and model reliability.
• Set up logging and alerting for model drift, latency, and failures in real-time.
• Control model versioning and manage model registries.

Data Pipeline Management

• Manage data registration, ingestion, and curation pipelines.
• Prepare and validate training and test datasets, ensuring proper dataset versioning.

Relevant Experience

• 3+ years of experience in ML acceleration, deployment, and operations.
• Proven expertise in optimizing deep learning models for edge devices.
• Experience with container orchestration (e.g., Kubernetes) for ML workflows.
• Strong skills in Python, C++, and relevant ML frameworks.
• Familiarity with AWS services for ML deployment and monitoring.
• Experience implementing robust testing, monitoring, and alerting for ML systems.
• Background in building and maintaining scalable data pipelines.

What You Bring

• Advanced experience with ML model optimization, deployment automation, and MLOps best practices.
• Strong understanding of containerization, orchestration, and cloud infrastructure.
• Proficiency in setting up monitoring and alerting systems for ML models.
• Ability to work cross-functionally with AI, robotics, and embedded systems teams.
• Strong problem-solving skills and a focus on operational reliability.

Bonus:

• Experience with UAVs or other autonomous systems.
• Background in agricultural technology or edge AI applications.