About this role

Build and productionize feedback loops that improve agent performance over time
Build the evaluation infrastructure – offline metrics, regression suites, and experiment analysis
Own the signal pipelines end-to-end: instrument events, build clean labeled datasets, and translate user behaviors into reliable learning signals
Design lightweight reinforcement learning / bandit-style approaches where appropriate
Partner closely with product and engineering to define success metrics and optimize for them
Design and analyze experiments that validate whether learning system changes actually improve real outcomes
Improve ranking, recommendations and decision making within the agent
Iterate quickly: Ship → measure → learn → improve

5-8 years hands on experience building and shipping ML systems
Bachelor’s or Master's degree in computer science
Experience shipping ML systems to production and have worked on recommendation systems, ranking, personalization or optimization problems
Deep knowledge in Python and model ML tooling
Pragmatic: you choose simple, effective solutions over theoretically perfect ones

Machine Learning Engineer – Relevance & Learning Systems

Key skills