5 months ago
Remote, WorldwideSenior
Base Salary
$150k - $215k/yr
Responsibilities
- Design and build scalable ML services, model training pipelines, and high-performance inference APIs for enrichment workflows.
- Deploy and optimize models using ONNX, vLLM, TensorRT, and related inference technologies for low latency and high throughput.
- Collaborate with software engineers and product teams on 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 with machine learning techniques, model optimization, efficient inference, and large-scale data processing.
Requirements
- At least 5 years of experience building and deploying machine learning systems in production environments.
- Strong proficiency with Kubernetes, Ray, ONNX, vLLM, TensorRT, or similar deployment and inference technologies.
- Proficiency with PyTorch, TensorFlow, and Jax for model training.
- Experience designing and scaling ML services that process large data volumes and meet strict latency and throughput requirements.
- Experience across the full ML lifecycle, including data preprocessing, feature engineering, training, evaluation, deployment, and monitoring.
- Solid software engineering skills with distributed systems, APIs, and cloud infrastructure.
- U.S. Person status is required because the role requires access to U.S.-only data systems.
Benefits
- Salary range of $150,000-$215,000 plus equity.
- Health, dental, and vision insurance.
- Remote-friendly work arrangement with WeWork access.
- Unlimited PTO, federal-holiday shared downtime, and company-wide year-end time off.
- 401(k) match and lifestyle and wellbeing stipends.
- Salary top-up during military reserve duty.
- Fully paid parental leave.
- Child and pet care reimbursement during travel.
Tech Stack
Categories
