You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Cantina

Research Scientist, Real-Time Video Generation

  • Remote

Salary

Not stated

Similar roles pay $120K - 215K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company builds real-time social AI, including models that bring characters to life with expression, personality and realism. Its flagship social AI platform is the first product in a wider ecosystem.

The role centres on real-time video generation for interactive characters, covering realistic humans, stylized characters and non-human identities. The characters need to speak, react and express themselves through face, gestures and body language.

The work combines several linked research problems: keeping a character's appearance consistent, making motion expressive and coherent, aligning speech with movement, and responding fast while generating reliably through an interaction. Quality, controllability and efficiency all count.

You will move between streaming generation, fine-tuning, distillation, inference optimization and data. Some problems need a new training method, while others are solved by better examples, better evaluation or finding a bottleneck in the implementation. Deciding which fix is worth the effort is part of the job.

You will have wide latitude to propose directions, explore unfamiliar ideas and help set the next priorities. The role suits someone who thrives with that freedom and can turn it into a steady run of useful experiments.

Responsibilities

  • Build models that respond in real time while keeping visual quality and consistency over time. Study latency, continuity and how behavior shifts during longer generations.
  • Explore how appearance, facial expression, gesture and body movement combine into one coherent character. Improve how speech and motion relate across identities and visual styles.
  • Adapt video models to new data, behaviors and capabilities. Test training objectives and conditioning methods, and carry promising ideas through implementation and evaluation.
  • Make generation faster and leaner, working on both model-level techniques and runtime changes. Measure each change's effect on quality, latency and memory.
  • Spend real time with the training examples. Find gaps in coverage and recurring failure modes, improve curation and sampling, and build data that teaches the intended behavior.
  • Design comparisons that show progress and make failures easy to understand. Pair quantitative metrics with close review of generated video and hands-on interaction with the model.
  • Read relevant research, reproduce and adapt useful methods, and share early experiments, demos and findings. Help the team decide which work gets more time and compute.

Requirements

  • Experience training or fine-tuning video or related generative models.
  • Ability to pick up unfamiliar methods quickly and turn them into working experiments.
  • Sound experimental judgment, a strong sense of ownership and clear communication.
  • Comfort with fast iteration and sharing results early.

Conditions

Compensation depends on skills, experience, job scope, location and competitive market data.

The company is an equal opportunity employer.

Benefits

  • Competitive salary and generous company equity.
  • Medical, dental and vision insurance, with the company covering 99.99% of premiums.
  • 42 days of paid time off: 15 PTO days, 10 sick days, 15 company holidays and 2 floating holidays.
  • Generous parental leave and fertility support.
  • 401(k) retirement savings plan.
  • Lifestyle spending account of $500/month, spendable however you like.
  • Complimentary lunch and snacks for employees working in the office.
  • One Medical membership, among other perks.

Where you’d work

Fully remote

You can work from

  • Europe
  • United States

About the company

Cantina

  • Industry: AI

Also hiring in Los Angeles, United States and San Francisco, United States

1 of their 7 open roles is remote

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 19 checks run
  • 3 red flags

Still hiring?

13 checks

2 red flags

How crowded?

6 checks

1 red flag

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details10 facts · Role, Location, Compensation, Employment, Company
Type
Full-time
Equity
Equity offered
Industry
AI
Specialty
Data Science
Region
United States
Pay period
Annual
Show 4 more factsShow less

Role

Category
Data & Analytics
Specialty
Data Science

Location

Work model
Remote
Region
United States
Remote from
  • Europe
  • United States

Compensation

Salary
Salary by agreement
Pay period
Annual
Equity
Equity offered

Employment

Type
Full-time

Company

Industry
AI

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason