Research Engineer - Post-Training RL & Distributed Learning
Location
United States + 180 moreAll locations: United States, Canada, Brazil, Colombia, Argentina, Chile, Venezuela, Bolivarian Republic Of, Bolivia, Plurinational State Of, Ecuador, French Guiana, Guyana, Paraguay, Peru, Suriname, Uruguay, Mexico, Costa Rica, El Salvador, Guatemala, Honduras, Nicaragua, Panama, Dominican Republic, Puerto Rico, Bahamas, Guadeloupe, Haiti, Jamaica, Martinique, Montserrat, United Kingdom, Germany, France, Estonia, Portugal, Hungary, Poland, Ukraine, Romania, Bulgaria, Czech Republic, Slovakia, Belarus, Moldova, Republic Of, Sweden, Greece, Belgium, Italy, Ireland, Switzerland, Netherlands, Finland, Malta, Denmark, Lithuania, Croatia, Spain, Austria, Bosnia And Herzegovina, Iceland, Luxembourg, Macedonia, The Former Yugoslav Republic Of, Montenegro, Norway, Serbia, Slovenia, Albania, Cyprus, Latvia, Monaco, South Africa, Egypt, Algeria, Angola, Benin, Botswana, Burkina Faso, Burundi, Cameroon, Cape Verde, Central African Republic, Chad, Congo, Côte D'ivoire, Congo, The Democratic Republic Of The, Equatorial Guinea, Eritrea, Ethiopia, Gabon, Gambia, Ghana, Guinea, Guinea-bissau, Kenya, Lesotho, Liberia, Libyan Arab Jamahiriya, Madagascar, Malawi, Mali, Mauritania, Mauritius, Mayotte, Morocco, Mozambique, Namibia, Niger, Nigeria, Réunion, Rwanda, Senegal, Seychelles, Sierra Leone, Somalia, Sudan, Swaziland, Tanzania, United Republic Of, Togo, Tunisia, Uganda, Zambia, Zimbabwe, Georgia, Turkey, Israel, United Arab Emirates, Armenia, Azerbaijan, Bahrain, Iraq, Jordan, Kuwait, Lebanon, Oman, Qatar, Saudi Arabia, Palestinian Territory, Occupied, Yemen, India, Japan, Philippines, Pakistan, Thailand, Singapore, Viet Nam, Taiwan, Province Of China, Indonesia, Cambodia, Lao People's Democratic Republic, Malaysia, Myanmar, Korea, Republic Of, China, Afghanistan, Bangladesh, Bhutan, Kazakhstan, Kyrgyzstan, Maldives, Mongolia, Nepal, Sri Lanka, Tajikistan, Turkmenistan, Uzbekistan, Australia, Papua New Guinea, Kiribati, Palau, French Polynesia, Tuvalu, New Zealand
Posted
5 days ago
Salary
Not specified
Seniority
Mid Level
Job Description
Role Description
Templar is looking for a Research Engineer to work across the post-training and pre-training stacks in a decentralized, community-driven training environment. You will contribute to state-of-the-art post-training pipelines running on real-world decentralized infrastructure, implement and evaluate ideas relevant to scaling large-scale post-training, and help push the frontier of what distributed LLM training can do. This is a research engineering role — you will be both building systems and contributing to the ideas that shape them. The environment is fast-moving, highly technical, and fully remote.
What You'll Do
- Contribute to the development of decentralized training of large language models
- Work across the post-training and pre-training stacks
- Implement and evaluate ideas relevant to scaling large-scale post-training on decentralized infrastructure
- Contribute to training runs and writing technical reports
Qualifications
- Strong programming skills with experience training models across multiple devices
- Solid foundations in machine learning
- Clear written and verbal communication skills
- Ability to work independently in a fast-moving, remote environment
Requirements
- Experience with LLM RL post-training or large-scale pre-training
- Publications or research experience in relevant areas such as distributed learning, reinforcement learning from human feedback, or scalable training infrastructure
Job Requirements
- Strong programming skills with experience training models across multiple devices
- Solid foundations in machine learning
- Clear written and verbal communication skills
- Ability to work independently in a fast-moving, remote environment
- Experience with LLM RL post-training or large-scale pre-training
- Publications or research experience in relevant areas such as distributed learning, reinforcement learning from human feedback, or scalable training infrastructure
Related Guides
Related Categories
Related Job Pages
More Research Engineer Jobs
Research Engineer (Focused on Search/IR)
FirecrawlThe easiest way to extract AI ready data from the web
The engineer will own and advance the search and information retrieval systems, building and operating everything from ingestion pipelines to serving layers for web content indexing at scale. Key tasks involve solving ranking, relevance, query understanding, and managing index freshness, deduplication, and incremental updates.
The role involves building reinforcement learning training infrastructure, reward pipelines, and fine-tuning systems to enhance web data extraction capabilities. Responsibilities include owning the full training loop from data collection to deployment and bridging classical RL approaches with modern LLM agent systems.
In this role, you will be responsible for actively participating in research, prototyping ideas, transforming research prototypes into production, and conducting code reviews. Your responsibilities will also include: Planning, implementing, and shipping end-to-end functionality. ...
Staff Research Engineer/Scientist
ServiceNowAs the AI platform for business transformation, we're putting AI to work across organizations — freeing people for work that matters. Making old tech work with new tech. Reaching across departments, from the front office to the back office and every office in between. Our ambition? To become the AI defining enterprise software company of the 21st century (or "AI DESCO21C," as we like to call it). With more than 8,100+ customers, we serve approximately 85% of the Fortune 500®, and we're proud to be a Fortune 100 Best Companies to Work For® and World's Most Admired Companies™. Explore your future career with us, visit www.servicenow.com/careers. From Fortune. ©2025 Fortune Media IP Limited. All rights reserved. Used under license.
The role involves researching, developing, and scaling Large Language Models at ServiceNow. Responsibilities include applying AI/ML methods, collaborating with cross-functional teams, and understanding product requirements to deliver high-quality solutions.
