Research Engineer (Reinforcement Learning)
Remote · Mid Level · Remote
Applicants who checked fit first are 3.1× more likely to hear back
Your score for this role already exists
ASAI compared this JD against 41 signals - skills, seniority, domain, stack overlap etc. Add a resume and it unlocks in about 30 seconds.
No credit card · 1 tap with Google
What we know about this role
LOW
livekit is showing limited hiring activity lately. Expect slight delayed response.
First 72 hours
Early applicants get seen before the pile builds.
Not a repost
The first time we've seen this listing - it hasn't been closed and reopened.
Skills required
10 listedYou almost certainly match several of these already. Unlock your skill map to see the matches, the gaps, and what to fix first.
Job description
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
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 protected].
Free · no signup
Get tomorrow's jobs before you have to search
Daily job drops, skill trends and free resources - posted straight to the group. Leave any time.
No spam. Just jobs and resources.
Why people use ASAI
Someone shared one job with you. ASAI keeps finding the rest.
Scored, not searched. Every role ranked against your actual profile.
Alerts as often as hourly. Reach new roles while the pile is still small.
Skill gaps, spelled out. See exactly which requirements you don't meet yet.
Verified jobs, only. Say no to ghost jobs. Your time deserves respect.