T
Senior ML Infrastructure Engineer
Tanya Osei
Full-time · Senior · Chicago
About the role
We are a two-sided marketplace for skilled trades — connecting homeowners with vetted electricians, plumbers, and HVAC technicians in 38 metropolitan areas. We have 2.1 million registered homeowners and 48,000 active trade professionals. The network effects are real: a denser supply side in a market makes the demand side convert better, which brings more demand, which makes supply more profitable, which attracts more supply. Our ML systems sit inside that loop. Ranking, matching, quality scoring, fraud detection, and dynamic pricing all feed into marketplace health metrics that we watch the same way an airline watches load factor. We are looking for a Senior ML Infrastructure Engineer to own the serving layer for the 12 models currently in production and the platform that the data science team uses to deploy new ones. The problems are practical: latency SLAs, model freshness guarantees, feature store reliability, and the kind of operational rigour that keeps a marketplace from degrading quietly over a weekend when no one is watching.
Responsibilities
- Own the model serving infrastructure for 12 production models, maintaining latency SLAs and uptime targets
- Build and maintain the real-time feature pipeline serving ranking and matching models
- Design and implement a feature store supporting both real-time serving and offline training data access
- Define and track ML infrastructure SLOs — latency, freshness, error rate — with dashboards and automated alerting
- Work with data scientists to establish deployment standards and reduce time from model approval to production
Requirements
- 6+ years of platform, MLOps, or data engineering with at least two years supporting a high-traffic production ML system
- Kubernetes for multi-tenant ML serving — you've managed resource contention, horizontal pod autoscaling, and serving latency SLOs
- Apache Kafka for real-time feature pipelines and event-driven model updates
- Apache Spark for batch feature computation and offline training data preparation
- MLflow for model registry, versioning, and serving lifecycle management
- AWS at depth: EKS, Kinesis, SageMaker, ElastiCache — you've run real serving infrastructure, not prototypes
- SQL for the data engineering that supports feature stores and model evaluation pipelines
Benefits
- Own the infrastructure that drives marketplace health metrics for a real two-sided marketplace at scale
- Full remote, US time zones preferred
- $135,000 – $160,000 base salary + equity
- $2,000 annual conference and tooling budget
- On-call is structured and compensated — two weeks per quarter with clear escalation paths
Job Type
Full-time
Level
Senior
Language
English
Salary Range
$135,000 – $160,000
AI Expertise
MLOps & AI Infrastructure
Ready to apply for this role?
Create a free talent account in under 2 minutes.
- Apply to verified AI companies
- Get AI-matched job recommendations
- Message hiring managers directly
- Build your public AI talent profile