Job Description

Location:

Remote / Hybrid (Preferred: Delhi NCR, India)

Type:

Full-Time | Core Team Role

Seniority:

Mid-Senior Level Ninja

About Us

We are building a

next-gen AI production lab

, where creativity meets computation. Our mission is to push the boundaries of generative AI for

cinematic storytelling, voice cloning, digital humans, virtual ads, and post-production workflows

. If you breathe creativity, love tinkering with models like GPT, SD, Sora, Runway, and can prompt magic from machines -- we want you.

Your Role: The Prompt Alchemist

As a Prompt Engineer, you are not just writing clever words -- you are

architecting input logic

that can guide multimodal AI systems (text, image, audio, video) to deliver

precise, creative, and consistent

outputs. You will work directly with our production and tech teams to build

prompt libraries, pipelines

, and

automated content flows

.

What You'll Own

Design, experiment, and iterate prompt frameworks for: Text-to-Image (e.g.,

Midjourney, Stable Diffusion

) Text-to-Video (e.g.,

Sora, Runway, Pika, Gen2

) Text-to-Audio/Voice (e.g.,

ElevenLabs, Bark, XTTS

, etc.) Text-to-3D or Motion (bonus) Work with

local deployments of models

using tools like:

AUTOMATIC1111

,

ComfyUI

,

InvokeAI

,

Local LLMs (LM Studio, Ollama)

Build and maintain

prompt templates

, chainable prompts, and

dynamic workflows

for scalable execution Collaborate with creative producers, animators, and ML engineers to integrate prompt logic into pipelines Research new tools, plugins, model behaviors, and

exploit them creatively

Analyze prompt outputs, debug inconsistencies, and evolve prompt engineering strategy

Your Superpowers (Must-Haves)

2+ years working hands-on with GenAI tools (you must have shipped real stuff) Proficiency in

prompting across all modalities

: text, image, video, voice Deep familiarity with tools like:

ChatGPT / Claude / Gemini

Midjourney, Leonardo, Playground, SDXL

Runway ML, Pika, Sora (conceptual), Genmo, D-ID

ElevenLabs, Bark, Tortoise, XTTS

Experience working with

local AI environments

(you should know how to fire up a local SD instance and load a LORA) Understanding of

model architecture behavior

(diffusion models, transformers, LLMs, etc.) Scripting ability (Python, Node.js or prompt pipelines with LangChain/Flowise is a bonus) Strong visual + verbal imagination -- you think like a creative, act like a coder

Bonus Points

You've contributed to open-source prompt libraries or AI projects You run a meme page or AI YouTube/TikTok channel You've worked in ad-tech, media, post-production, or virtual humans You can explain the difference between a Negative Prompt and a Prompt Weight You know how to automate batch generations or run model inference APIs

What We Offer

Core founding team position with

equity opportunities

Access to cutting-edge AI models (and GPUs) A sandbox environment for building

next-gen creative tools

A collaborative team of builders, misfits, creators, and tech rebels Freedom to

experiment and break stuff (responsibly)

Job Types: Full-time, Permanent

Pay: ?10,868.13 - ?36,765.22 per month

Benefits:

Work from home
Schedule:

Day shift
Supplemental Pay:

Performance bonus
Application Question(s):

what Video tool you have used what Audio gen tool you have used Any End to end video production experience you have
Work Location: Remote