S

Reinforcement Learning Engineer

surge group • United States
Visa Sponsorship
Apply Now
AI Summary

Design and build reinforcement learning environments and agent tasks that challenge AI agents on realistic coding, finance and enterprise workflows. Create rewards, verifiers and evaluations for RLHF/RLVR, run experiments and measure data quality and downstream model impact. Requires 1–8 years of software engineering or ML experience, strong Python/TypeScript skills and RL/LLM post-training familiarity.

Key Highlights
On-site in San Francisco, five days per week
Build RL environments, rewards and evaluations for LLM post-training
1–8 years relevant software engineering or ML experience
Visa support available (H-1B, O-1, TN, STEM OPT)
$220k–$290k base plus $200k–$300k bonus and equity

Searching for Development & Programming roles that provide visa sponsorship? Connect with international employers through Development & Programming Jobs with Visa Sponsorship opportunities actively seeking talented professionals.

Key Responsibilities
Build RL environments and agent tasks across coding, finance and enterprise workflows
Design rewards, scoring rubrics, verifiers and evaluations for RLHF and RLVR
Investigate model failures and reward exploitation
Build and maintain real-world and synthetic data pipelines
Run experiments on environment designs and reward formulations
Measure dataset quality, diversity and downstream impact
Improve human feedback workflows and annotator consistency
Translate partner labs' training objectives into specifications
Build reproducible, scalable infrastructure using containerisation
Technical Skills Required
Python TypeScript Docker

Explore our comprehensive directory of visa sponsorship jobs from employers worldwide who are ready to sponsor talented international professionals.

Benefits & Perks
Equity
Bonus $200,000–$300,000
Visa sponsorship support

Interested in opportunities specifically in United States? Discover our dedicated Visa Sponsorship Jobs in United States page featuring roles from top employers in this location.

Nice to Have
RL environment development including internships or research projects
Agent benchmarking, AI safety evaluations or reward-hacking research
Building automated verifiers, evaluation harnesses or reward models
Designing synthetic tasks or measuring training-data quality and diversity
Docker or similar containerisation tools
Published AI research or open-source contributions
Early-stage startup or founding experience

Job Description

Reinforcement Learning Engineer

Location: San Francisco, CA — on-site, five days per week

Employment: Full-time

Compensation: $220,000–$290,000 base + $200,000–$300,000 bonus + equity

About the company

Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

Ready to apply?

Apply Now
See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources
Job Overview
Posted Nov 02, 2026
Employment Full-time
Experience Mid-Senior level
Location United States
Category Programming
Company surge group
Keep exploring

Similar Jobs

Explore other opportunities that match your interests

BeaconFire Inc.

United States

Java Developer

Programming Full-time Entry level 1h ago

  • AI
  • Angular
  • C++
  • C#
Visa

Visas, Work Permits & Legal Insights

Stay informed about visa types, work permits, and immigration updates for international professionals.

Browse all articles

Subscribe to our newsletter

New visa sponsorship, relocation and remote tech jobs, delivered to your inbox.