ML Engineer / Data Scientist - Reinforcement Learning

Remote – Latin America, 6 AM – 2 PM Pacific TimeFull-TimeMiddle

Salary not disclosed

Apply NowOpens the employer's application page

Job Details

5+ years of experience in Python software engineering
3+ years of experience in Data Science, Machine Learning, or Environment Engineering roles
Strong practical experience working with AI systems, including prompt engineering
Hands-on experience with AI frameworks such as LangChain, LangGraph, or MCP servers
Solid understanding of reinforcement learning concepts, including reward modeling, environment dynamics, and agent interaction loops
Experience working with metrics, instrumentation, and data pipelines for ML or RL systems
Ability to work 6 AM – 2 PM Pacific Time
Experience with tools such as Codex or Claude Code (Preferred)
Background in integrating AI systems into production environments (Preferred)
Familiarity with evaluation frameworks for large language models (Preferred)
Strong self-management and ability to plan and execute work independently (Preferred)

Design and implement reinforcement learning (RL) environments for large-scale agent evaluation and experimentation
Build task generation pipelines, dynamic datasets, and controlled simulation environments with varying complexity
Develop reward models and verification systems to automatically evaluate model outputs and reasoning paths
Collaborate with infrastructure teams to ensure systems are scalable, reproducible, and fully instrumented for telemetry
Design APIs and orchestration frameworks to manage agent lifecycle across environments
Optimize performance, logging systems, and reward consistency in distributed environments
Contribute to continuous improvements in evaluation methodologies and AI behavior alignment

View Full Description & ApplyYou'll be redirected to the employer's site