LLM Engineer at Spellbrush (W18)
Making Anime Real
San Francisco
Full-time
About Spellbrush

Here at Spellbrush, we're passionate about making a good anime game. We also happen to be the world's leading generative AI studio — we're the team behind niji・journey. We are currently investigating how AI can be used to help human artists perform masterpieces in the most complex medium of our times: videogames. Our games are characterized by a no-compromise approach to well-balanced gameplay married to a truthful love of visual arts. If you love turn-based tactics games, please consider applying!

About the role

Here at Spellbrush , we're passionate about making a good anime game.

We also happen to be the world's leading generative AI studio — we're the team behind niji・journey.

We are currently investigating how AI can be used to help human artists perform masterpieces in the most complex medium of our times: videogames.

Our games are characterized by a no-compromise approach to well-balanced gameplay married to a truthful love of visual arts.

If you love turn-based tactics games, please consider applying!

The Role:

Spellbrush, the world’s leading generative AI studio behind_ niji・journey __ , _ is looking for an LLM Prompt Engineer to bring the characters and world in our mobile turn-based tactics game to life with distinctive flair! If you love games like Fire Emblem and Final Fantasy Tactics and are eager to utilize Generative AI to create evocative gameplay experiences, please apply!

What you’ll do:

  • Become the power user and wizarding wordsmith of our LLM models, coaxing out new turns of phrase, emotional responses, and vivid imagery through imaginative prompt engineering.

  • Deeply understand our next flagship game’s core narrative, themes, and character motivations and conflicts – then translate these elements into elegant LLM prompts.

  • Work with our Creative Director to develop new systems for enabling our game’s characters to freely express themselves in the native game platforms where they interact with players.

  • NOTE: You do not need to be currently involved in LLM research or an AI / ML expert to apply - we highly value your writing and creative ability.

You might be a great fit if:

  • You endeavor to use LLM’s to revolutionize character communications.
    A familiarity with text-based Generative AI and LLM is definitely handy, but moreso than that you understand that LLM’s are working off of datasets and training, and that your finesse in guiding the models will produce outstanding delights of diction.

  • You’re eager to push the boundaries of written and verbal communications.
    Part of the challenge (and excitement) of using LLM’s is that they can produce combinations of words and phrases to produce meanings, mental images, and interactions never before imagined.

Maybe you’ve devised a new alien language for a sci-fi novel or a mana system for an underground race of mushroom people. Whatever it is, going beyond the norm in your creativity will help our LLM models reach their limitless potential.

  • You understand what it means to be human, and how our human tendencies emerge in conversation.
    To make authentic and genuine conversations, we believe the author (or in this case, prompter), should have a deep familiarity with the nuances that make language feel more “human”. Whatever your mode of introspection and emotional exploration, we’d love to know (and support it)!

  • The anime aesthetic resonates with you.
    It's no secret – we're huge anime enthusiasts, and our work focuses on the anime aesthetic. Your work will enable characters to partake in the full spectrum of emotions and reactions with unique personality, whether yandere, tsundere, or a new archetype you invent! (This is a check to see if you're reading thoroughly - craft a little "tweet" written by an anime character in the Anything Else you'd like us to know" question!)

  • You're comfortable working on small, fast-paced, on-site teams
    Working here will feel very much like a small indie studio: close-knit, with high ownership and flexibility. We’re also an in-person studio. Our games team is at our office in downtown San Francisco, CA, 3-4x a week!

  • And you're excited about the potential of Generative AI.
    You'll also be working closely with some of the best AI researchers in the world. Part of working with our team will involve looking at our latest research results and figuring out how to apply them to the game best. You will be at the cutting edge of what is possible with machine learning, art, and games.

The final base salary is dependent upon location, experience, fit, and other factors. In addition, we offer a generous compensation package that includes equity, top-tier employer-sponsored health, dental, and vision insurance, and additional perks!

At Spellbrush, we value creativity, collaboration, and innovation. If you're excited about working with cutting-edge technology and passionate about anime, gaming, and generative AI, we’d love to hear from you!

To apply - please share your previous work experience/resume, writing portfolio, sample or prompt engineering sample, and the name of the best waifu or husbando in your message!

Technology

At Spellbrush, we're pushing the boundaries of generative networks through our state-of-the-art diffusion text-to-image research. There's no shorted of interesting tech challenges here:

  • Research: We make heavy use of Pytorch and JAX, and train large-scale models using both TPUs and GPUs. Our researchers spend each day developing and testing novel state-of-the-art diffusion models.
  • Engineering: We make use of a lot of Elixir for real-time backend systems, Python for machine learning, and lots of simulation and game logic code written in C# via Unity. We also have tons of internal tools and apps written in Typescript, React, and RN.
  • Infrastructure: We've done everything from building our own in-house GPU supercomputer, to scaling up massive inference clusters in our own datacenters, typically orchestrating via some unholy combination of SLURM, kubernetes, and NATS.

Other jobs at Spellbrush

fulltimeTokyo, JP / San Francisco, CA, US / Remote (Tokyo, JP; San Francisco, CA, US)Embedded systems$75K - $200K3+ years

fulltimeSan FranciscoFull stack

fulltimeChiyoda City, Tokyo, JP / San Francisco, CA, US / RemoteMachine learning$75K - $200KAny (new grads ok)

fulltimeSan Francisco, CA / Tokyo, JP / RemoteFull stack$60K - $180K3+ years

fulltimeSan Francisco, CA / Chiyoda City, Tokyo, JP / RemoteFrontend$60 - $1803+ years

Hundreds of YC startups are hiring on Work at a Startup.

Sign up to see more ›