Research Engineer (Reinforcement Learning)
Remote$135k - $300kFull-timePosted 2mo ago
About the role
Role focused on building post-training systems for LiveKit agents, including environments, data pipelines, training experiments, evaluations, and production deployment for voice and text agents.
Responsibilities
- Build the environments and verifiers our models train against
- Own the synthetic data pipeline, from generation through the quality gates
- Run training experiments end to end, and explain what moved the model
- Build the evaluations a release has to clear
- Choose and adapt open-weight base models for our tasks
- Make trained behavior hold up for voice and text agents alike
- Ship models into production and keep improving them on real usage
Qualifications
- A strong Python engineer
- Have carried a model from raw data through to production
- Treat data as the product: coverage, diversity, leakage
- Assume a model will exploit a weak reward, and design against it
- Comfortable with GPUs and honest about their limits
- Know when to train, and when not to
- Comfortable working collaboratively in a remote environment
Skills
Required:PythonProduction ML deploymentData as a product (coverage, diversity, leakage)Collaboration in remote environments
Nice to have:Reinforcement learning / post-training practices
Benefits
- Health, dental, and vision benefits
- Flexible vacation policy
- Competitive salary and equity package
Last updated Sep 30, 2026. Interested? Apply on the company site.
About LiveKit
Build voice, video, and physical AI | LiveKit
Open source agent framework and cloud platform for apps that see, hear, and speak.
livestreamingorchestrationroboticsvoice AIvoice-ai-stack
More open roles at LiveKit
- Revenue Accounting Manager4d agoRemote · G&A
- Senior Product Operations Manager1w agoRemote · R&D
- GTM Strategic Finance Manager1mo agoRemote · G&A
- Senior Developer Advocate, Social1mo agoRemote · S&M
- Startup Program Lead1mo agoHybrid (San Francisco, CA (Hybrid)) · S&M