Research Engineer (Reinforcement Learning)
Posted Aug 19 (91 days ago) · Last updated Nov 18
Posted Aug 19 (91 days ago)
Key facts
Remote reinforcement learning engineer building and deploying voice and text agents at LiveKit.
How this salary compares
Est. take-home €5,808 - €11,706
- Field
- Software engineering
- Languages required
English
Original job ad
About the role
Summarised by JobCrawls from the job ad above.
Requirements
- Strong Python engineering skills
- Experience taking a model from raw data through to production
- Treats data quality, coverage, diversity and leakage as important
- Can anticipate and mitigate models exploiting weak rewards
- Comfortable with GPUs and aware of their limitations
Show 2 more
- Can judge when model training is appropriate
- Able to collaborate in a remote environment
Responsibilities
- Build model training environments and verifiers
- Own the synthetic-data pipeline from generation through quality gates
- Run end-to-end training experiments and explain model changes
- Build release evaluations
- Choose and adapt open-weight base models
Show 2 more
- Ensure trained behavior works for voice and text agents
- Deploy models to production and improve them based on real usage
Skills & technologies
Show 8 more
Benefits & perks
About LiveKit
| Location | Active listings |
|---|---|
| APJ | 4 |
| EMEA | 4 |
| North America | 4 |
| Role type | Active listings |
|---|---|
| Distributed Systems Engineer | 2 |
| Reinforcement Learning Engineer | 1 |
| Software Engineer | 1 |
| Role level | Active listings |
|---|---|
| Senior | 3 |
| Mid-Level | 1 |
LiveKit builds infrastructure for voice-driven computing. Its platform helps developers build, test, deploy, scale and observe production agents, and powers voice AI applications for OpenAI, xAI, Salesforce, Coursera, Spotify and thousands of others.
