AI/ML Engineer

Pixels on Target LLC is hiring an AI/ML Engineer to develop and deploy deep learning models for real-time edge systems. The role covers dataset and pipeline development, model optimization for edge hardware, integration with embedded systems, and validation and deployment of production-ready ML capabilities.

Responsibilities:

• Design, train, and evaluate deep learning models for classification, prediction, anomaly detection, and sensor data analysis
• Build end-to-end ML pipelines: data collection, labeling, cleaning, augmentation, training, evaluation, and versioning
• Optimize models for real-time inference on edge hardware (e.g. NVIDIA Jetson) using quantization (FP16/INT8), pruning, distillation, TensorRT, and ONNX
• Profile and reduce latency, memory, and power across the full inference pipeline to meet onboard compute budgets
• Integrate ML models into embedded and production systems in close collaboration with the embedded and hardware teams
• Develop multimodal approaches that combine data from multiple sensors and sources
• Explore and apply emerging techniques such as transformers, large language models, generative AI, reinforcement learning, and foundation models where they improve mission performance
• Build synthetic data generation and data replay tools for model training and validation
• Set up evaluation benchmarks, metrics, and regression tests to track model performance across environments and edge cases
• Support field testing, data capture, and debugging of deployed systems
• Contribute to system architecture, performance analysis, validation testing, and deployment (MLOps) pipelines
• Drive rapid prototyping and move promising concepts into production-ready systems