Research Engineer (Reinforcement Learning)
At LiveKit · North America; EMEA; NAMER
Salary: US$135,000–300,000 a year
- Engineering
- Full-time
See how well you match Match me reads your CV and picks the jobs that suit you best.
Get jobs like this within hours Radar emails you new jobs open to you within hours of us finding them, before most people see them.
Where you can work from
Open to EMEA and North America
“North America”
From the location.
“EMEA”
From the location.
“NAMER”
From the job board field.
Which countries count as EMEA?
Albania, Algeria, Andorra, Angola, Austria, Bahrain, Belgium, Benin, Bosnia and Herzegovina, Botswana, Bulgaria, Burkina Faso, Burundi, Cameroon, Cape Verde, Central African Republic, Chad, Comoros, Côte d'Ivoire, Croatia, Cyprus, Czechia, Denmark, Djibouti, DR Congo, Egypt, Equatorial Guinea, Eritrea, Estonia, Eswatini, Ethiopia, Faroe Islands, Finland, France, Gabon, Gambia, Germany, Ghana, Gibraltar, Greece, Guernsey, Guinea, Guinea-Bissau, Hungary, Iceland, Iran, Iraq, Ireland, Isle of Man, Israel, Italy, Jersey, Jordan, Kenya, Kosovo, Kuwait, Latvia, Lebanon, Lesotho, Liberia, Libya, Liechtenstein, Lithuania, Luxembourg, Madagascar, Malawi, Mali, Malta, Mauritania, Mauritius, Moldova, Monaco, Montenegro, Morocco, Mozambique, Namibia, Netherlands, Niger, Nigeria, North Macedonia, Norway, Oman, Palestine, Poland, Portugal, Qatar, Republic of the Congo, Romania, Rwanda, San Marino, São Tomé and Príncipe, Saudi Arabia, Senegal, Serbia, Seychelles, Sierra Leone, Slovakia, Slovenia, Somalia, South Africa, South Sudan, Spain, Sudan, Sweden, Switzerland, Syria, Tanzania, Togo, Tunisia, Türkiye, Uganda, Ukraine, United Arab Emirates, United Kingdom, Vatican City, Yemen, Zambia, Zimbabwe.
Not everyone includes Afghanistan, Armenia, Azerbaijan, Belarus, Georgia, Kazakhstan, Kyrgyzstan, Pakistan, Russia, Tajikistan, Turkmenistan, Uzbekistan, so for those we say “Unclear”.
Which countries count as North America?
Canada, United States.
Not everyone includes Antigua and Barbuda, Bahamas, Barbados, Belize, Costa Rica, Cuba, Dominica, Dominican Republic, El Salvador, Grenada, Guatemala, Haiti, Honduras, Jamaica, Mexico, Nicaragua, Panama, Puerto Rico, Puerto Rico, Saint Kitts and Nevis, Saint Lucia, Saint Vincent and Grenadines, Trinidad and Tobago, so for those we say “Unclear”.
Report a mistake
- Posted
- 18 August 2026
- First seen by us
- 4 October 2026
- Last checked
- 10 hours ago
Job description
From LiveKit’s job post, as they wrote it.
About LiveKit
LiveKit is building the infrastructure layer for the voice-driven era of computing. Our platform gives developers everything they need to build, test, deploy, scale, and observe agents in production. Founded in 2021, LiveKit powers voice AI applications for OpenAI, xAI, Salesforce, Coursera, Spotify, and thousands of others, collectively facilitating billions of calls each year.
About This Role
Read the full description
We are looking for an exceptional engineer to build post-training at LiveKit. Our agents run over voice and increasingly over text channels like SMS and chat, and the interesting problems show up over long horizons: staying useful across many sessions, working with context that accumulates over time, and using tools reliably in the middle of a live conversation.
What You'll Do
* 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
Who You Are
* 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
Nice to Have
* Experience with post-training: fine-tuning, reward design, or reinforcement learning such as GRPO
* RL and fine-tuning frameworks such as TRL, verl, or OpenRLHF, or a training loop you wrote yourself
* Fast rollouts with vLLM or SGLang, multi-GPU training with FSDP
* Training tool-using or multi-turn agents
* Execution sandboxes, verifiers, eval harnesses, or tooling other engineers depend on
* Open-weight families such as Qwen or Llama, LoRA and similar
Our Commitment to You
* The opportunity to shape the brand of a fast-growing developer platform
* Collaboration with a small, senior team that deeply values craft and creativity
* Competitive salary and equity package
* Health, dental, and vision benefits
* Flexible vacation policy
LiveKit is an equal opportunity employer and does not discriminate on the basis of any characteristic protected by applicable law. If you require a reasonable accommodation during the application or interview process, please contact [email removed].
Research Engineer (Reinforcement Learning)LiveKit
Apply on LiveKit (opens in a new tab)Get jobs like this by email
Once a week, we email the new remote jobs open where you live, each with the line that proves it. Every email has a one-click unsubscribe.