Tech Stack

Description

You'll design and maintain cloud infrastructure to support real-time ML model serving, data ingestion, and evaluation workflows. You'll deploy and optimize APIs for low-latency access to ML models and embedding search systems, working closely with ML engineers and researchers to build infrastructure that makes high-performance models accessible and reliable in production.

Requirements

• 3–8 years of experience deploying machine learning systems or high-availability backend systems
• Has shipped and maintained production infrastructure at scale, supporting ML workflows
• Experience with GCP, AWS, or similar platforms (including managed ML services)
• Proficient in Terraform, Docker, Kubernetes, or similar infra tools
• Understands performance tradeoffs in serving models and embedding search pipelines
• Can work cross-functionally with ML, security, and product teams to deploy safely and iterate fast
• Brings a builder's mindset and bias for ownership in ambiguous environments

Responsibilities

• Design and maintain cloud infrastructure (GCP or AWS) to support real-time model serving, data ingestion, and evaluation workflows
• Deploy and optimize APIs for low-latency access to ML models and embedding search systems
• Manage and optimize the end-to-end training data flow—from sourcing and cleaning datasets to preparing them for model consumption—ensuring accuracy, scalability, and efficiency
• Build observability tooling for production ML pipelines (monitor latency, error rates, request volumes, drift)
• Automate model deployment, retraining, and evaluation pipelines (CI/CD for ML)
• Work with ML engineers to package models for serving
• Help manage vector databases and semantic search infrastructure (e.g., Pinecone, FAISS, Vertex Matching Engine)
• Ensure security, compliance, and uptime of infrastructure supporting safety-critical systems