Senior ML Infra Architect — Production AI Platform

Unchain Data; Bellevue (WA); On-site; USD 209,000 - 245,000; Full time

Benefits offered by this job

Health insurance

Equity ownership

401(k) matching

Bonus opportunities

Catered meals and office perks

Job summary

Robinhood is hiring for a Senior Software Engineer on the AI Infrastructure team to own the architecture and end-to-end delivery of foundation systems powering model development, deployment, and observability. You will lead architecture for the feature store, model serving, and training infra, working with ML practitioners to accelerate their work.

The role emphasizes senior judgment on complex problems, cross-team collaboration, and mentoring engineers.

Qualifications

• 6+ years of software engineering experience in ML infrastructure, data engineering, or model operations.
• Demonstrated ability to own and deliver complex platform systems end-to-end, from architecture to production.
• Deep expertise in model serving, distributed systems, and production ML workflows at scale.
• Strong proficiency in Python, C++, or similar languages, with experience in ML frameworks such as TensorFlow or PyTorch.
• Solid knowledge of modern ML infrastructure tooling (Ray, Kubeflow, SageMaker, TensorFlow Serving, Triton).
• Hands-on experience with large-scale search systems and dense vector search (Qdrant/ChromaDB/Elasticsearch).
• Experience influencing technical direction and mentoring engineers.

Responsibilities

• Lead architecture and end-to-end delivery of scalable ML deployment, monitoring, and management systems in production.
• Own technical direction for platform areas—model serving, feature store, observability infrastructure.
• Collaborate with ML practitioners, data engineers, and applied AI teams to streamline workflows and accelerate experimentation.
• Scale the feature store to support real-time and batch feature retrieval with low latency.
• Define and implement robust observability standards for model performance and data pipelines.
• Manage cloud compute resources (CPU/GPU) on AWS for cost-effective, high-throughput training and inference.
• Contribute to technical strategy and mentor engineers through design reviews and hands-on guidance.

Skills

ML infrastructure

Distributed systems

Python/C++

TensorFlow/PyTorch

Model serving

Vector databases

Leadership/Mentoring

Education

Bachelor’s degree in CS/SE

Advanced degree a plus

Tools

Ray

Kubeflow

SageMaker

TensorFlow Serving

Triton

Qdrant/ChromaDB/Elasticsearch

Job description

Robinhood is hiring for a Senior Software Engineer on the AI Infrastructure team to own the architecture and end-to-end delivery of foundation systems powering model development, deployment, and observability. You will lead architecture for the feature store, model serving, and training infra, working with ML practitioners to accelerate their work.

The role emphasizes senior judgment on complex problems, cross-team collaboration, and mentoring engineers.