Machine Learning Engineer

PRADCO Inc. is applying applied machine learning to wildlife imagery, turning tagged camera observations into deer movement predictions and hunt location optimization. In this onsite role in Massachusetts, you will help own the prediction ML lifecycle, from model design and training through deployment and ongoing monitoring.

You will build a prediction layer that translates behavioral signals into stand recommendations for hunters, working across computer vision, time-series modeling, and ML operations.

Responsibilities

• Design and train object detection and classification models (for example YOLOv8, RT-DETR, or similar) to identify deer presence, sex, age class, and antler characteristics from trail camera imagery.
• Build and maintain an end-to-end ML pipeline including data ingestion from cloud storage, preprocessing, training on GPU clusters, evaluation, and deployment using Triton, TorchServe, or comparable serving infrastructure.
• Develop deer re-identification models using coat patterns and antler morphology to track individual animals across cameras and time.
• Engineer features by combining vision outputs with environmental context such as weather, terrain, moon phase, and a rut calendar to support downstream behavioral prediction models.
• Use ML Ops tooling such as Mlflow or Weights & Biases for experiment tracking, model versioning, and staged production deployments.
• Partner with Data Engineering to optimize data pipelines, and with a Wildlife Biologist advisor to validate model outputs against real-world deer behavior.
• Monitor model performance in production and implement retraining pipelines to handle data drift across seasons.

Requirements

• 4+ years of experience in machine learning engineering, with demonstrated experience in production deployments.
• PyTorch proficiency; experience with Ultralytics/YOLO or similar detection frameworks is strongly preferred.
• Strong foundations in CNN architectures, transfer learning, and domain adaptation.
• Experience deploying models on GPU infrastructure such as AWS SageMaker, GCP Vertex AI, or equivalent services.
• Proficiency in Python, plus familiarity with data pipeline tooling like Kafka or Airflow (or similar).
• Solid ML evaluation skills including confusion matrices, mAP, precision/recall tradeoffs, and the ability to diagnose model failures.
• Familiarity with time-series prediction approaches such as LSTMs, Prophet, and XGBoost for temporal data.

Technology Focus

• PyTorch, Ultralytics/YOLO (YOLOv8), RT-DETR
• Triton, TorchServe, Mlflow, Weights & Biases
• AWS SageMaker, GCP Vertex AI, Python, Kafka, Airflow
• CNN architectures, LSTMs, Prophet, XGBoost

Essential Job Function

• Experience with re-identification (RelD) or few-shot learning tasks.
• Prior work on wildlife imagery, agricultural computer vision, or similar low-contrast, occlusion-heavy domains.
• Experience with Microsoft Azure.
• Passion for the outdoors or hunting is a genuine plus, since domain empathy supports better product outcomes.