ML Platform Engineer — Scalable AI Infra

Whatnot; Seattle (WA); Hybrid; USD 245,000 - 345,000; Full time

Benefits offered by this job

Health Insurance

Work From Home Support

Care benefits

Retirement—401k with employer match

Dogfood budget

Parental Leave

Job summary

Whatnot seeks an engineer to design and scale the core infrastructure powering AI and ML in a rapidly growing live shopping marketplace. You will collaborate with ML scientists to deploy self-hosted models, building systems for low-latency serving and high-throughput GPU inference.

Ideal candidates have 3+ years building production systems, strong Python skills, and experience with modern databases and cloud services. Remote-friendly with in-person hubs in US regions.

Qualifications

• Bachelor’s degree in CS, stats, math, or related field, or equivalent work experience.
• 3+ years building production systems for consumer-scale loads.
• 1+ years of Python development.
• Experience with PostgreSQL, DynamoDB, Elasticsearch, Redis.
• Familiarity with monitoring tools (DataDog, Grafana).
• Cloud exposure with AWS services (SageMaker, Lambda, Kinesis, S3, EC2, EKS/ECS, Kafka, Flink).
• Strong remote collaboration and reproducible work practices.
• Excellent documentation and communication.

Responsibilities

• Own the infrastructure powering AI/ML models across critical surfaces.
• Prototype, deploy, and productionalize novel ML architectures that shape user experience.
• Design and scale inference infrastructure with low latency and high throughput.
• Build distributed training and inference pipelines leveraging GPUs.
• Tackle new technical challenges as we scale AI across Whatnot’s ecosystem.

Skills

Python

Remote collaboration

Software design

Documentation

Education

Bachelor's degree in CS or related field

Equivalent work experience

Tools

PostgreSQL

DynamoDB

Elasticsearch

Redis

DataDog

Grafana

AWS

Kafka

Flink

Job description

Whatnot seeks an engineer to design and scale the core infrastructure powering AI and ML in a rapidly growing live shopping marketplace. You will collaborate with ML scientists to deploy self-hosted models, building systems for low-latency serving and high-throughput GPU inference.

Ideal candidates have 3+ years building production systems, strong Python skills, and experience with modern databases and cloud services. Remote-friendly with in-person hubs in US regions.