Senior ML Engineer — Real-Time Pricing & Scale (Equity)

Alt; United States; Hybrid; USD 235,000 - 250,000; Full time

Benefits offered by this job

Work-from-home stipend

Wellness stipend

Office stipend

401(k) retirement benefits

Job summary

Alt is building real-time pricing at scale for the $5B trading-card market. We seek an experienced ML engineer to own model lifecycle, from feature generation to production deployment and monitoring, partnering with domain experts to improve pricing coverage and accuracy.

You will design experiments, reduce infrastructure costs, and ensure low-latency, scalable model serving on AWS. A startup pace and ownership mindset are essential.

Qualifications

• Must-have: 7+ years engineering, 5+ years shipping production ML/AI models.
• Deep Python/SQL production skills with feature pipelines and robust validation.
• Experience with gradient-boosted/ensemble models and domain-specific tuning.
• Experience using LLMs/foundation models in production.
• Familiarity with MLflow or similar experiment tracking tool.
• Experience owning production AWS model-serving infra and scaling.
• CI/CD orchestration and IaC for cloud infra.

Responsibilities

• Own ML lifecycle from training to deployment and monitoring.
• Improve pricing & underwriting models to reduce costs while increasing accuracy.
• Collaborate with domain experts to align models with market judgment.
• Design experiments and backtests to validate new features.
• Ensure production APIs are scalable and low-latency.

Skills

Python

SQL

Feature engineering

Model deployment

AWS

CI/CD

Experiment tracking

LLMs

Memory/timeout debugging

Cross-functional collaboration

Tools

MLflow

Terraform

Kubernetes

Git

Airflow

Job description

Alt is building real-time pricing at scale for the $5B trading-card market. We seek an experienced ML engineer to own model lifecycle, from feature generation to production deployment and monitoring, partnering with domain experts to improve pricing coverage and accuracy.

You will design experiments, reduce infrastructure costs, and ensure low-latency, scalable model serving on AWS. A startup pace and ownership mindset are essential.