ML Platform Engineer: Scale AI & Inference

Apply; San Francisco (CA); Hybrid; USD 245,000 - 345,000; Full time

Benefits offered by this job

Flexible Time Off

Health Insurance

Work From Home Allowance

Parental Leave

401k + matching

Job summary

Whatnot is seeking an AI/ML Platform Engineer to design and scale the core infrastructure powering machine learning and self-hosted LLM apps. You’ll work with ML scientists to bring cutting-edge models into production and unlock new product experiences with low-latency serving and high-throughput inference.

You will own inference pipelines, GPU-accelerated training, and distributed systems while collaborating in a remote-friendly, hub-based environment.

Qualifications

• Bachelor’s degree in Computer Science, Statistics, Applied Mathematics or a related technical field, or equivalent work experience.
• 3+ years of software engineering experience building and maintaining production systems for consumer-scale loads.
• 1+ years of professional experience developing software in Python.
• Experience with operational, search, and key‑value databases such as PostgreSQL, DynamoDB, Elasticsearch, Redis.
• Firm grasp of visualization tools for monitoring and logging e.g. DataDog, Grafana.
• Familiarity with cloud computing platforms and managed services such as AWS Sagemaker, Lambda, Kinesis, S3, EC2, EKS/ECS, Apache Kafka, Flink.
• Professionalism around collaborating in a remote working environment and well tested, reproducible work.
• Exceptional documentation and communication skills.

Responsibilities

• Own the infrastructure powering AI and ML models across critical business surfaces–supporting growth, recommendations, trust and safety, fraud, seller tooling, and more.
• Prototype, deploy, and productionalize novel ML architectures that directly shape user experience and marketplace dynamics.
• Design and scale inference infrastructure capable of serving large models with low latency and high throughput.
• Build distributed training and inference pipelines leveraging GPUs and both model and data parallelism.
• Stretch beyond your comfort zone to take on new technical challenges as we scale AI across Whatnot’s ecosystem.

Skills

Python

Documentation

Communication

Remote collaboration

Problem solving

Education

Bachelor's degree in CS/Stats/Math or related field

Tools

PostgreSQL

DynamoDB

Elasticsearch

Redis

DataDog

Grafana

AWS Sagemaker

Lambda

Kinesis

S3

EC2

EKS/ECS

Apache Kafka

Flink

Job description

Whatnot is seeking an AI/ML Platform Engineer to design and scale the core infrastructure powering machine learning and self-hosted LLM apps. You’ll work with ML scientists to bring cutting-edge models into production and unlock new product experiences with low-latency serving and high-throughput inference.

You will own inference pipelines, GPU-accelerated training, and distributed systems while collaborating in a remote-friendly, hub-based environment.