Machine Learning Engineer

Role overview

Vannevar is hiring a Machine Learning Engineer to help build and operate the end-to-end ML platform for mission-critical data enrichment. You’ll develop scalable ML services, from training and fine-tuning to deploying low-latency inference in production.

Responsibilities

• Design and build scalable ML services for enrichment workflows, including training pipelines and high-performance inference APIs
• Deploy and optimize models using inference frameworks and libraries (e.g., ONNX, vLLM, TensorRT) to achieve low latency and high throughput
• Partner with product and software teams to define data requirements, feature engineering strategies, and model evaluation metrics
• Build monitoring, observability, and evaluation systems to maintain model quality and service reliability in production
• Stay current on emerging ML techniques, especially model optimization, efficient inference, and large-scale data processing

Requirements

• 5+ years building and deploying machine learning systems in production
• Strong proficiency with model deployment and serving technologies (e.g., Kubernetes, Ray) and inference libraries (e.g., ONNX, vLLM, TensorRT)
• Proficiency with ML training frameworks (PyTorch, TensorFlow, Jax)
• Experience scaling ML services for large-volume data processing with strict latency/throughput requirements
• Experience across the full ML lifecycle: preprocessing, feature engineering, training, evaluation, deployment, and monitoring
• Solid software engineering skills: distributed systems, APIs, and cloud infrastructure
• U.S. Person status required to access U.S.-only data systems

Nice-to-haves

• Not explicitly stated, but experience with production observability/evaluation systems and efficient inference/model optimization is emphasized.