Staff ML Engineer — Real-Time Rewards & Loyalty AI Architect

Mistplay Inc.; Oakland (CA); On-site; USD 180,000 - 220,000; Full time

Benefits offered by this job

Equity

Team lunches and company events

Career growth opportunities

Job summary

Mistplay is seeking a Staff Machine Learning Engineer to lead the design and optimization of our rewards economy. You will develop and balance reward systems to attract and retain users while maintaining sustainable unit economics, collaborating with Data and AI on real-time predictive modeling and optimization.

You will translate complex model outputs into strategic insights for executives, implement contextual bandits and RL frameworks for personalized rewards, and partner with Product,

Qualifications

• 8+ years in data science, ML, econometrics, or a related field.
• Experience with reinforcement learning (DeepQ, contextual bandits).
• Proficiency in Python and PyTorch; strong SQL/data analysis skills.

Responsibilities

• Lead the rewards economy strategy for Mistplay and optimize core loops.
• Create and implement ML-driven rewards systems balancing user value and economics.
• Analyze and optimize economy strategies to boost engagement and business outcomes.
• Translate model outputs into actionable executive insights for AI-first decisions.
• Design productionizable contextual bandits and RL frameworks for real-time rewards.
• Collaborate with Product, Analytics, Engineering, and Finance to align incentives with business goals.

Skills

8+ years data science / ML / economet

reinforcement learning

Python

PyTorch

SQL / data analysis

Education

MS/PhD in Data Science or related quantitative field

Tools

Python

PyTorch

SQL

Job description

Mistplay is seeking a Staff Machine Learning Engineer to lead the design and optimization of our rewards economy. You will develop and balance reward systems to attract and retain users while maintaining sustainable unit economics, collaborating with Data and AI on real-time predictive modeling and optimization.

You will translate complex model outputs into strategic insights for executives, implement contextual bandits and RL frameworks for personalized rewards, and partner with Product,