Machine Learning Engineer

Heven AeroTech • Sterling, VA

3d

About The Position

At Heven AeroTech (Heven), we don’t just believe in the power of people—we build our success on it. As a recognized leader in hydrogen powered drones, we’ve earned recognition for creating a workplace where innovation thrives, collaboration is second nature, and every employee feels valued. Our culture is anchored in trust, and a shared commitment to excellence. We know that great organizations are built by extraordinary teams. That’s why we invest in your professional growth, offering robust training programs, leadership development opportunities, and a clear pathway for advancement. At Heven, your voice matters, your ideas are heard, and your contributions make a tangible impact.

The Machine Learning Engineer will architect and deploy production AI/ML systems that power autonomous aerospace operations from edge to cloud. This role involves building and maintaining the complete ML lifecycle—spanning from data pipelines to deployed models—with a focus on computer vision for autonomous navigation, LLMs for mission planning, and agentic AI for enterprise optimization. The position requires taking full ownership of system reliability, performance, and the operational excellence necessary to enable next-generation autonomous Unmanned Aircraft Systems (UAS).

Requirements

• Bachelor's degree in Computer Science, Applied Mathematics, or related technical field
• 5+ years building production ML systems; 3+ years with Google Cloud Platform
• Google Professional Machine Learning Engineer Certification (current or obtainable within 1 month)
• Expert Python; production experience with TensorFlow or PyTorch
• Computer vision systems: object detection, segmentation, tracking
• Edge deployment with TensorFlow Lite, TensorRT, or ONNX; model optimization experience
• MLOps: CI/CD, monitoring, experiment tracking
• Experience deploying LLMs and RAG systems
• U.S. Person status; ability to obtain DoD Secret clearance within 6 months

Nice To Haves

• Edge hardware deployment (NVIDIA Jetson, Google Coral TPU)
• Embedded Linux and ROS experience
• Defense/aerospace industry background
• Additional Google Cloud certifications
• Domain expertise: GPS-denied navigation, sensor fusion, UAV/drone systems, or adversarial ML

Responsibilities

• Build data processing and training pipelines using Google Cloud
• Develop computer vision models for obstacle detection, target recognition, and sensor fusion
• Implement automated retraining workflows and experiment tracking systems
• Create CI/CD pipelines for model deployment
• Optimize models for edge devices through quantization, pruning, and compression
• Deploy inference pipelines on UAS hardware with power and memory constraints
• Implement visual-inertial odometry for GPS-denied navigation
• Develop over-the-air updates and offline-capable systems with network fallback
• Integrate sensor fusion algorithms (camera, LiDAR, radar, IMU)
• Monitor model performance, latency, and availability against SLAs
• Build drift detection, A/B testing, and alerting systems
• Troubleshoot production issues and maintain audit trails
• Deploy and fine-tune LLMs for mission planning
• Build RAG systems and agentic AI workflows for enterprise operations

Benefits

• medical, dental, and vision coverage
• retirement plans
• paid time off/sick
• additional protections such as critical illness, hospital indemnity, accident coverage, and short- and long-term disability

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level