Log inSign up free
  • Home
  • Jobs
    • Applications
    • Career
    • Resume
    • Cover letters
    • Job X-ray
  • Studio
  • More tools
    • Profile
    • Hiring
  • Settings
All jobs
REReactor logo

Reactor

Location not stated

Serverless infrastructurefor real-time AI..

DATA & ML
Models
All ModelsEvery frontier world model behind one API.SandboxTry every model in one place.
Platform
ModelsEvery frontier world model behind one API.ServeBring real-time AI to your applications.RoboticsBring real-time intelligence to the physical world.
DocsBlog
Resources
CareersOpen positions at Reactor.Slack CommunityMeet other developers building with Reactor.StartupsCredits and support for early teams.
Log inGet started
Dashboard

Reactor Serve

Serverless infrastructurefor real-time AI.

Deploy, optimize and build with real-time models.

Request access Read the docs
Your modelReactor ServeAny device
Demo session ws-7f3aworld-model · us-west live
ingest
infer
stream
frames60.0fps
latency8ms
sessions1,284
gpuB300×8
p50 8 ms
sfoiadyyzlhrfrabomsinnrtsyd

Deploy real-time AI. Anywhere.

Bring any model, deploy it to GPUs reserved for you, and run real-time AI from a browser, a phone or a robot.

Bring your modelDeploy at scaleConnect any client
from reactor_runtime import ReactorApp, MediaInput, Output
from reactor_runtime import Video, event

class Inputs(MediaInput):
    webcam: Video

class Outputs(Output):
    main_video: Video

class MyWorldModel(ReactorApp):
    media: Inputs
    fps = 30

    def load(self, config_path):
        self.pipe = load_pipeline(config_path)

    def generate(self, frame):
        return self.pipe.step(frame, self.prompt)

    @event(name="set_prompt")
    def set_prompt(self, prompt: str):
        self.prompt = prompt
+.24−.08+.61+.12−.32+.47+.09−.16+.18+.73−.25+.42+.56−.11+.38+.07
class MyWorldModel(ReactorApp): def setup(self): self.model = load_model("v2") def generate(self, frame): inputs = self.preprocess(frame) output = self.model(inputs) if output is None: return frame return self.encode(output)
  1. Reactor runtimeRuns and optimizes your model
  2. Your inference code
  3. Your weights
reactor
$ reactor model deployUsing model spec from reactor.yaml (world-explorer:v1.3.0)Applying model configuration... ✓Deploying release v1.3.0 to us-west, us-east, eu-west... ✓ ✓ Deployed  Model    world-explorer  Release  v1.3.0  Rollout  rolling, no sessions dropped
world-explorerv1.3.0 · 4 instances · 3 regions
Live
Sessions44 live
60300-14s-7snow
Frame time13 ms
20136-14s-7snow
us-west4 ready
us-east2 ready
eu-west0/1 starting
import { Reactor } from "@reactor/sdk";

const reactor = new Reactor({
  modelName: "world",
  jwt,
});
await reactor.connect();
reactor.publishTrack(gamepad);
reactor.sendCommand("set_prompt", {
  prompt: "night falls",
});
World modelsReal-time videoAvatarsRobotics
Live30 fps12 msSet prompt

Bring your own stack

Diffusers, custom CUDA kernels or a VLA policy: if it runs in Python on a GPU, it runs on Serve.

Any modality

Stream out video, audio, joint targets or JSON at the real-time rate you set.

Your code, your rules

State, moderation and command handling stay plain Python you own, with no framework to learn.

If it’s real time, it runs on Reactor.

Build the next generation of applications with models that respond as people, environments and interfaces change.

World models

Interactive worlds for games, simulation and training data, generated in real time.

Avatars

Video agents for support, tutoring and companionship that listen and reply face to face.

Real-time video

Generate video and audio faster than real time for live streams, ads and editing tools.

Robotics

Run robot policies and world models in the cloud, connected to your robots in real time.

Explore Reactor Robotics
+

And more

Have another use case in mind? Bring your model and run it on Reactor.

Tell us what you’re building

Close to your users. Built for low latency.

Global by default

An extensive network of compute regions worldwide. Deploy close to your users across major clouds.

Production-grade streaming

Stream video, audio and data in both directions over WebRTC, QUIC or gRPC. Send inputs and commands to your model and receive outputs as they’re generated.

ApplicationModel
videoaudiodata

Performance at every scale.

Capacity

Scale across regions

Add GPU capacity across regions, right from one platform. Your model code stays the same.

Inference

Get more from every GPU

Our inference team tunes your model with custom kernels and a real-time engine to serve more sessions per GPU.

Deployment

Instant deployment

Deploy your world model with one command. We take care of GPU capacity, real-time connections and monitoring.

~/my-modelzsh
$reactor model deploy
✓ Configuration validated✓ GPU capacity provisioned✓ Model release deployed

Deployment ready.

Waiting for connections...

$

The right compute for your real-time model.

Choose NVIDIA GPUs or AWS Trainium for your model.

NVIDIA

NVIDIA Blackwell

For the largest world models and video pipelines at full frame rate.

  • B200180 GB HBM3e
  • B300270 GB HBM3eOn request
  • GB200186 GB HBM3eOn request
  • GB300279 GB HBM3eOn request
  • RTX 6000 Pro96 GB GDDR7
NVIDIA

NVIDIA Hopper

Where most real-time models land, with one H100 per instance by default.

  • H10080 GB HBM3Default
  • H200141 GB HBM3e
Amazon Web Services

AWS Trainium

For models compiled for Neuron, in AWS regions.

  • Trainium 3144 GB HBM3eOn request

More hardware coming soon.

Reserved

Capacity committed to your model. Choose your hardware and region, and keep it ready for steady traffic.

Reserve capacity

On demand

Capacity available at a moment’s notice. Pay by the minute for the compute your sessions use.

Get started

Powering real-time world model sessions for

  • Overworld
  • Amap
  • Alibaba Group
  • LTX
  • MiniMax
  • ByteDance
  • Vidu
  • NVIDIA
  • Visko
  • Saturn Dynamics
  • Overworld
  • Amap
  • Alibaba Group
  • LTX
  • MiniMax
  • ByteDance
  • Vidu
  • NVIDIA
  • Visko
  • Saturn Dynamics

Reactor Serve

The next generation of AI runs in real time.

Bring your world models, avatars, and robot policies to production with inference, GPU scaling, and streaming on one platform.

[email protected] ↗

Contact us about Serve

Your contact detailsNameWork emailCompany (optional)What are you building? (optional)Request access↗
Stay up-to-date with Reactor
GET IN TOUCH

Product

  • Platform
  • Enterprise
  • Startups
  • Pricing
  • Status

Developers

  • Documentation
  • Slack Community

Company

  • Blog
  • Careers
  • Brand kit

Legal

  • Terms of Service
  • Privacy Notice

© 2026 REACTOR TECHNOLOGIES, INC.
ALL RIGHTS RESERVED.

    Pay
    Not stated
    Where
    Not stated
    Work
    Not stated
    Type
    Not stated
    Posted
    20 Nov, 2026
    Visa
    Sponsorship unknown
    Apply on the original postingSign in to apply

    Unverified board

    Seen open on its job board in the last 3 days.

    Open since at least 20 Nov, 2026.

    Visa sponsorship

    Unknown: ask at the first call

    Why, and where it comes fromHide the evidence

    Foly found no public US visa filings for this employer. That isn't a no: the posting doesn't say either way.

    • Source: US Department of Labor, LCA disclosure data
    • No records imported yet.

    At the first recruiter call, ask: “Does this role support visa sponsorship, now or in the future?” before more rounds.

    Public data, not legal advice. For your own situation, ask your school's international office or an immigration attorney.

    more at Reactor.

    20 Nov, 2026

    Reactor

    Real-time AI infrastructure for video, robotics, and world models.

    REReactor logo
    • Data & ML
    Seen open on its job board in the last 3 days

    Location not stated

    Salary not listed

    Details
    20 Nov, 2026

    Reactor

    GTM Engineer

    REReactor logo
    • Full time
    • Engineering
    Seen open on its job board in the last 3 days

    Location not stated

    Full time

    Details
    20 Nov, 2026

    Reactor

    Technical Product Marketing Manager

    REReactor logo
    • Full time
    • Sales & Marketing
    Seen open on its job board in the last 3 days

    Location not stated

    Full time

    Details