Senior Reinforcement Learning Engineer

Senior Reinforcement Learning Engineer
Specialization: RLHF | GRPO | Policy Optimization | AI Evaluation
Location: Philippines | 100% Remote
IMPORTANT: PHILIPPINES-BASED APPLICANTS ONLY
This opportunity is exclusively open to candidates currently residing in the Philippines. Applications from candidates based outside the Philippines will not be considered.
Have You Built AI Models That Actually Learn and Improve?
We're looking for engineers who don't just use AI — they know how to train it.
We're seeking an exceptional Senior Reinforcement Learning Engineer with proven, hands-on experience in reinforcement learning, policy optimization, reward design, and AI model evaluation.
This is an opportunity to apply your expertise to technically challenging AI research and engineering initiatives within a dynamic, internationally focused technology environment.
You'll collaborate with experienced technical professionals, solve complex engineering problems, and contribute to meaningful advancements in AI model performance.
If you've built it, trained it, optimized it, and measured the results, we'd love to hear from you.
What You'll Do
Design, implement, and optimize reinforcement learning training pipelines.
Apply RL algorithms such as PPO, GRPO, or equivalent techniques to improve model performance.
Develop and refine reward functions, reward models, and policy optimization approaches.
Conduct RLHF, RLAIF, or related model post-training experiments.
Design and execute AI model and agent evaluation frameworks.
Analyze training performance, investigate failures, and implement improvements.
Collaborate with technical teams to translate research into practical engineering solutions.
Document experiments, findings, and measurable outcomes.
What We're Looking For
Required Qualifications
Proven, hands-on experience personally implementing and running reinforcement learning training using PPO, GRPO, or equivalent RL algorithms.
Demonstrated experience in policy optimization, reward design, or reward-based model training.
Practical experience conducting RL experiments and evaluating measurable outcomes.
Strong Python programming skills and hands-on experience with PyTorch or equivalent machine learning frameworks.
Solid understanding of reinforcement learning algorithms, model training, and optimization techniques.
Experience developing and evaluating AI models or intelligent agents.
Ability to independently troubleshoot training challenges and improve model performance.
Strong analytical, mathematical, and technical problem-solving abilities.
Excellent technical communication and documentation skills.
Must currently reside in the Philippines.
You'll Stand Out If You Have
Hands-on experience with RLHF, GRPO, PPO, RLAIF, or reward modeling.
Experience in LLM post-training, preference optimization, or model alignment.
Experience building or evaluating AI agents and multi-step reasoning systems.
Familiarity with Hugging Face TRL, Ray RLlib, DeepSpeed, or similar frameworks.
Experience designing automated evaluation benchmarks and testing pipelines.
Contributions to AI research, technical publications, or open-source projects.
Experience in multimodal learning or other advanced machine learning applications.
Why Explore This Opportunity?
Challenging Technical Work: Apply your RL expertise to complex AI engineering and research initiatives.
Meaningful Ownership: Take responsibility for technical implementation, experimentation, and measurable results.
Research Meets Engineering: Work on problems that require both strong theoretical foundations and practical execution.
Collaborative Environment: Work alongside experienced technical professionals and leadership.
International Exposure: Contribute to technology initiatives with an international outlook.
Remote Flexibility: Work from anywhere within the Philippines.
Show Us What You've Built
We value demonstrated technical accomplishments over impressive-sounding job titles.
We're particularly interested in engineers who have personally implemented RL training pipelines, optimized policies, developed reward mechanisms, and delivered measurable improvements.
How to Apply
Submit your updated CV along with relevant GitHub repositories, research publications, or technical portfolio.
Please include details of at least one reinforcement learning project you've personally implemented, highlighting:
RL Algorithm: PPO, GRPO, or equivalent technique used.
Your Contribution: What you personally trained, implemented, or optimized.
Technical Stack: Frameworks and technologies used.
Results: Measurable training improvements or evaluation outcomes.
Important: Experience limited to prompt engineering, chatbot development, RAG applications, AI workflow automation, or RLHF data annotation without direct RL training or optimization experience does not meet the requirements for this position.
Ready for Your Next Technical Challenge?
Bring your expertise. Show us what you've built. Let's explore what's next.
We'd love to hear from experienced RL engineers who are ready to apply their skills to challenging AI initiatives.

Work arrangement
Yes