About the job

BetterGroup (the team behind BetterPic and BetterStudio) is a profitable AI startup scaling fast, millions in revenue, millions of requests, and increasing GPU workloads across multiple products. On BetterPic, our AI makes professional headshots accessible to anyone, fast, affordable, and 4K studio-quality. Now we’re expanding into B2B, building high-impact workflows for teams and partners. On BetterStudio we’re solving photoshoots for fashion ecommerce.

We’re looking for a ComfyUI Workflows Developer to build, optimize, and debug powerful image generation pipelines using ComfyUI’s node-based system. This isn’t a casual hobbyist role, we need someone who understands the full pipeline, from prompt logic and conditioning to batch execution and quality tuning.

If you’ve built advanced workflows around human image generation, face similarity, and Lora/Checkpoint training, we want to talk.

We value your time, here’s what matters…

Team Perks

Meet your Team

All headshots generated using Betterpic ❤️

About you

What You’ll Be Doing

• Build and optimize ComfyUI workflows for human-centered image generation (portraits, faces, headshots, fashion)

• Debug node chains, optimize runtime and quality, and refactor inefficient workflows

• Integrate workflows with external systems (e.g., REST APIs, Node.js, Python scripts)

• Run batch inference, image comparison, and post-processing logic at scale.

• Analyze outputs, find weak points and improve workflows based on customer and team feedback

• Implement dynamic configuration: variable inputs, conditional prompts, re-routable node flows

• Maintain a local repo of reusable and production-grade workflows

• Help train or fine-tune checkpoints/Loras when needed (especially for Flux-style pipelines)
  

Who We’re Looking For

Must-Have Traits

• At least 6 months of hands-on ComfyUI experience (including setup, compositing workflows from scratch, custom node research and modification)

• Deep interest in GenAI technology, understanding of current and upcoming diffusion models, knowledge of their architecture, capabilities and limitations

• Experience creating workflows optimized for realism and face similarity, with attention to detail and quality of outputs.

• Knowledge and experience in using visual detection models, controlnets, style models, and other adjacent tools for in-depth manipulation of latents, conditions, images and masks.

• Experience with optimizing compute and memory resources to decrease cost, increase pipeline stability, and scale image generation

• Comfortable with GitHub, scripting in Python, and basic API integrations
  

Strong Bonus Points

• Skilled in training Loras and fine-tuning checkpoint, especially for Flux or SDXL models.

• Worked with Huggingface tools, diffusers, or related image model libraries

• Can build integrations or scripts to connect ComfyUI to external services (Node.js, Express, etc.)

• Experience in implementing workflows to real production pipelines, communication with front-end, back-end and support to ensure successful deployment

• Has a strong portfolio of readable and comprehensive ComfyUI workflows focused on human subjects, inpainting, automated image manipulation
  

Why This Matters
We’re running high-volume production pipelines powering BetterPic and BetterStudio, our workflow quality directly impacts output quality, user retention, and brand trust. This is not only R&D for fun, it’s pipeline engineering with real business impact.

Our Stack

• Backend: Node.js, Express, PostgreSQL, Redis, AWS

• Frontend: Nuxt 3, Vue 3, TypeScript, TailwindCSS

• Infra: AWS (S3, SES, Cloudfront), Render, Cloudflare, Supabase, and our own decentralized BetterContainer to run your workflows :)

• Tools: GitHub, Prettier, Slack, Asana
  
  

Application Process

1. Fill out this form

2. [Take Home] Coding Challenge (1-3 hours)

• 2.1. Small development challenge

• 2.2. Brief [5 minutes max] Loom video explaining functionality, implementation and design decisions

3. Interview with the CTO (30 minutes)

4. Interview with the rest of the management team (30 minutes)

5. Offer from BetterPic

Final Notes
You must show, not tell, we’re only looking for real ComfyUI practitioners who’ve built workflows that hold up in production. If you have examples of:

• Face similarity workflows

• Batch generation with quality gating

• Custom conditioning logic

…we want to see them.

Join us and shape the visual backbone of BetterGroup’s AI engines.

Let’s build something lasting.