onsite
Machine Learning Engineer - Embedded Insights - Plaid
ML Engineer
Lead the design and deployment of machine‑learning models on embedded platforms, optimizing performance and resource usage while collaborating with cross‑functional teams to deliver scalable financial insights.
About the role
Key Responsibilities
- Design, train, and optimize ML models for real‑time inference on embedded devices used in financial applications.
- Collaborate with firmware and hardware teams to integrate models into low‑power, resource‑constrained environments.
- Develop end‑to‑end pipelines from data ingestion to model deployment, ensuring data quality and compliance.
- Implement model compression, quantization, and edge‑specific optimizations to meet latency and memory constraints.
- Monitor model performance in production, iterate on improvements, and maintain robust versioning and CI/CD workflows.
Requirements
- 3+ years of experience in machine‑learning engineering, with a strong focus on embedded or edge deployments.
- Proficiency in Python, TensorFlow/PyTorch, and C/C++ for performance‑critical code.
- Hands‑on experience with model compression techniques (quantization, pruning) and deployment tools (ONNX, TensorRT).
- Solid understanding of data pipelines, version control, and CI/CD practices.
- Excellent problem‑solving skills and ability to work collaboratively in a fast‑paced environment.
Skills
pythonmachine learningtensorflow