ComfyUI Engineer.
North America
June 25, 2026 at 6:54 AM
✨ AI summary
Location
- US Remote (global)
Languages
- Python
- TypeScript
- JavaScript
Frameworks
- ComfyUI
- diffusers
- PyTorch
- Hugging Face
- Node.js
Cloud Services
- AWS
- Cloudflare R2
- Modal
- Neon
Databases
- PostgreSQL
- Redis
Experience Level
- Senior
Home Careers ComfyUI Engineer
All careers
We're hiring
Own the workflows that power millions of AI images every month. You think in nodes, you debug in graphs, you care obsessively about output quality.
Remote
Senior IC + equity
Apply now How we hire
workflow_headshot_v3.jsonrunning
Load Checkpoint flux-dev-fp16 CLIP Encode "portrait, 4k" ControlNet face-pose-v2 KSampler steps: 28 cfg: 7.0 euler_a seed: 42819 Output FaceDetailer sim: 0.92
The role
Runflow is the AI image and video infrastructure layer for production. We power the AI headshots, fashion shoots, and product photography that companies like BetterPic and BetterStudio ship every day, millions of images a month, with quality scored before delivery.
We're hiring a ComfyUI Engineer to own the workflows that produce them. This isn't a research role. You'll ship production workflows that directly impact output quality, customer retention, and revenue. You're the person who decides which checkpoints, which LoRAs, which control nets, which sampler, and how it all stays under VRAM and latency budgets at scale.
If you debug node graphs in your sleep, train LoRAs for fun, and have strong opinions on face similarity vs. likeness preservation, this is for you.
Quick facts
TeamWorkflows
Reports toHead of AI
LocationRemote
CompensationSenior IC + equity
StartASAP
Representative projects
What you'd ship in your first 6 months.
Concrete, shippable, on the live roadmap. Not hypothetical. We expect every one of these to land.
Project 01
Ship a face-similarity workflow that holds 99%+ likeness across 500-image batches
Pick the checkpoints, design the conditioning chain, calibrate the IP-Adapter / face-swap stack, and run the eval. Hand it off to Sentinel for live scoring.
Project 02
Cut p95 latency on the BetterStudio pipeline by 40%
Profile VRAM, swap samplers, prune the graph, parallelise where it pays. The win has to hold across realistic batch shapes, not synthetic benchmarks.
Project 03
Train a domain-specific LoRA from scratch for a new product vertical
Curate the dataset, set up the training loop, ship the LoRA into the workflow, validate against held-out evals. Document the recipe so the next vertical takes a week instead of a month.
Responsibilities
What you'll be doing.
You'll own the full lifecycle, from prototype to production at scale.
Build, optimise, and debug ComfyUI workflows for human-centric and product image generation
Profile node chains. Cut VRAM, latency, and cost without sacrificing quality
Wire workflows into Runflow's Solutions API, Python, TypeScript, REST
Run batch inference and post-processing at production scale (millions/mo)
Iterate on output quality. Hand off failure modes to Sentinel; learn from its scores
Build dynamic conditioning systems, variable poses, styles, backgrounds, products
Maintain a versioned, documented workflow repo other engineers can read
Train and fine-tune checkpoints + LoRAs (Flux, SDXL, Wan-style pipelines)
Requirements
About you.
You may be a good fit if…
A specific number of years. A specific degree. A specific stack. We hire on whether you can ship end-to-end and whether you have taste. Everything else is noise.
Tech stack
What we work with.
Backend
Node.jsPythonPostgreSQLRedis
Workflow
ComfyUIdiffusersPyTorchHugging Face
Infra
AWSCloudflare R2ModalNeon
Tools
GitHubLinearSlackSentinel
How we hire
Five steps. Decision speed is part of the offer.
We move fast because senior candidates with multiple offers reward the team that respects their time. Whole loop fits in two weeks.
01/5
Application submitted
Form, ~5 min
We read every word of every application. No silent rejections, ever.
Triaged within 5 business days
Apply now
02/5
Take-home challenge
2 hours max, your time
A small, real Runflow problem. We score the prompts and decisions you made as much as the output itself.
Reviewed within 3 business days
03/5
30 minutes with the CTO
30 min, live
Quick conversation about your take-home, the team, and how you work day-to-day.
Decision in 48 hours
04/5
Paid challenge, 2 days
2 days, we pay for your time
A bigger problem we pay you to work through. We care about outcomes, not process. AI tools more than welcome.
Decision in 48 hours
05/5
Closing interview
90 min, live
Casual chat with the two founders.
Decision in 24 hours
Show, don't tell.
We value proof over promises. When you apply, include examples. Things that stand out:
Face-similarity workflows with consistent identity preservation across batches
Batch generation pipelines with quality gating built in
Custom conditioning logic or node modifications you wrote yourself
LoRA training results and the methodology you used
Apply
Ready to ship?
Five minutes. We read every word. Yes / no / not-now within 5 business days, always.
You're applying for ComfyUI Engineer
Email*
Location
optional, city, country, time zone
Links*
At least one, LinkedIn, GitHub, portfolio, Loom, anything.
Show us 1–3 things you've built that prove you can ship end-to-end.*
Repos, posts, demos, anything. Specifics beat resume bullets.
1500 left
What's a problem you solved with AI as the execution layer, not just chat?*
We care that you reach for AI as a default tool, not occasionally.
1000 left
Show us a product you find beautiful. Why?*
Taste is non-negotiable. We want your real opinions.
800 left
Which AI tools are in your daily workflow?
Pick all you actively use, not just tried.
How much is AI helping you these days?
A sentence or two. Skeptical, force multiplier, in between, where it shines, where it doesn't.
600 left
Share a Claude Code session that shipped a feature end-to-end.
Optional but high-signal. We want to see how you actually work with AI, the prompts, the back-and-forth, the corrections. Whole session, snippet, Loom, gist, anything.
3000 left
When have you most successfully hacked a non-computer system to your advantage?
Optional. Bureaucracy, supply chain, a conference badge, social dynamics, anything. We collect signal here.
1000 left
Most recent role + company
Just the title + company name. We don't need a CV.
200 left
When could you start?
Salary expectation
Confidential. A range is fine.
200 left
Share an actual ComfyUI workflow you're proud of.*
The workflow IS the portfolio. Paste the JSON, link a Gist, link a Loom of you walking through the graph, anything that lets us actually see it. If it ran in production at scale, even better, tell us about the volume + the gnarliest debug it survived. Written-only descriptions are a soft no.
5000 left
Anything else?
Optional. A short note, a question, a relevant detail we missed.
500 left
We commit to a yes / no / not-now within 5 business days. Always. No silent rejections.
Other open roles
Maybe one of these instead.
We hire builders, not roles. If none fit exactly, the open application is at the bottom.
Sentinel·Remote
Help build the AI quality scoring layer Runflow runs in front of every image and video we ship. Hands-on ML, in production tomorrow, at scale.
View role
Infrastructure·Remote
Build the infrastructure that powers the next generation of AI media. GPU fleet, warm workers, queues, FastAPI services, in production tomorrow.
View role
DevRel·Remote
Ship cool things on top of Runflow, bring creators in, drive adoption of the next generation of AI image + video infrastructure.
View role
Open·You define it
Open application
Don't see your role? Tell us what you'd build at Runflow and how it moves the mission forward.
Apply openly
All careers
We're hiring
- Workflows
Own the workflows that power millions of AI images every month. You think in nodes, you debug in graphs, you care obsessively about output quality.
Remote
- global
Senior IC + equity
Apply now How we hire
workflow_headshot_v3.jsonrunning
Load Checkpoint flux-dev-fp16 CLIP Encode "portrait, 4k" ControlNet face-pose-v2 KSampler steps: 28 cfg: 7.0 euler_a seed: 42819 Output FaceDetailer sim: 0.92
The role
Runflow is the AI image and video infrastructure layer for production. We power the AI headshots, fashion shoots, and product photography that companies like BetterPic and BetterStudio ship every day, millions of images a month, with quality scored before delivery.
We're hiring a ComfyUI Engineer to own the workflows that produce them. This isn't a research role. You'll ship production workflows that directly impact output quality, customer retention, and revenue. You're the person who decides which checkpoints, which LoRAs, which control nets, which sampler, and how it all stays under VRAM and latency budgets at scale.
If you debug node graphs in your sleep, train LoRAs for fun, and have strong opinions on face similarity vs. likeness preservation, this is for you.
Quick facts
TeamWorkflows
Reports toHead of AI
LocationRemote
- global
CompensationSenior IC + equity
StartASAP
Representative projects
What you'd ship in your first 6 months.
Concrete, shippable, on the live roadmap. Not hypothetical. We expect every one of these to land.
Project 01
Ship a face-similarity workflow that holds 99%+ likeness across 500-image batches
Pick the checkpoints, design the conditioning chain, calibrate the IP-Adapter / face-swap stack, and run the eval. Hand it off to Sentinel for live scoring.
Project 02
Cut p95 latency on the BetterStudio pipeline by 40%
Profile VRAM, swap samplers, prune the graph, parallelise where it pays. The win has to hold across realistic batch shapes, not synthetic benchmarks.
Project 03
Train a domain-specific LoRA from scratch for a new product vertical
Curate the dataset, set up the training loop, ship the LoRA into the workflow, validate against held-out evals. Document the recipe so the next vertical takes a week instead of a month.
Responsibilities
What you'll be doing.
You'll own the full lifecycle, from prototype to production at scale.
Build, optimise, and debug ComfyUI workflows for human-centric and product image generation
Profile node chains. Cut VRAM, latency, and cost without sacrificing quality
Wire workflows into Runflow's Solutions API, Python, TypeScript, REST
Run batch inference and post-processing at production scale (millions/mo)
Iterate on output quality. Hand off failure modes to Sentinel; learn from its scores
Build dynamic conditioning systems, variable poses, styles, backgrounds, products
Maintain a versioned, documented workflow repo other engineers can read
Train and fine-tune checkpoints + LoRAs (Flux, SDXL, Wan-style pipelines)
Requirements
About you.
You may be a good fit if…
- You've shipped ComfyUI in production for 6+ months, setup, custom nodes, debugging gnarly graphs
- You have deep working knowledge of diffusion models (SDXL, Flux, the open-source release of the month)
- You've built workflows tuned for realism and identity preservation, face similarity is second nature
- You're comfortable with ControlNets, IP-Adapters, segmentation, and the full conditioning toolbox
- You optimise compute. You know when to swap a sampler vs. retrain a LoRA
- You're fluent in GitHub, Python, and REST, the workflow is just one part of a system
- Have trained LoRAs or fine-tuned checkpoints (Flux/SDXL/Wan) end to end
- Use the diffusers library and Hugging Face tooling fluently
- Have built integrations connecting ComfyUI to external services (Plytix, Shopify, custom CMSes)
- Have shipped production pipelines at scale (>100K images/day) and lived to tell the war stories
- Have a public portfolio of workflows you'd be proud to walk us through
A specific number of years. A specific degree. A specific stack. We hire on whether you can ship end-to-end and whether you have taste. Everything else is noise.
Tech stack
What we work with.
Backend
Node.jsPythonPostgreSQLRedis
Workflow
ComfyUIdiffusersPyTorchHugging Face
Infra
AWSCloudflare R2ModalNeon
Tools
GitHubLinearSlackSentinel
How we hire
Five steps. Decision speed is part of the offer.
We move fast because senior candidates with multiple offers reward the team that respects their time. Whole loop fits in two weeks.
01/5
Application submitted
Form, ~5 min
We read every word of every application. No silent rejections, ever.
Triaged within 5 business days
Apply now
02/5
Take-home challenge
2 hours max, your time
A small, real Runflow problem. We score the prompts and decisions you made as much as the output itself.
Reviewed within 3 business days
03/5
30 minutes with the CTO
30 min, live
Quick conversation about your take-home, the team, and how you work day-to-day.
Decision in 48 hours
04/5
Paid challenge, 2 days
2 days, we pay for your time
A bigger problem we pay you to work through. We care about outcomes, not process. AI tools more than welcome.
Decision in 48 hours
05/5
Closing interview
90 min, live
Casual chat with the two founders.
Decision in 24 hours
Show, don't tell.
We value proof over promises. When you apply, include examples. Things that stand out:
Face-similarity workflows with consistent identity preservation across batches
Batch generation pipelines with quality gating built in
Custom conditioning logic or node modifications you wrote yourself
LoRA training results and the methodology you used
Apply
Ready to ship?
Five minutes. We read every word. Yes / no / not-now within 5 business days, always.
You're applying for ComfyUI Engineer
- Workflows
Email*
Location
optional, city, country, time zone
Links*
At least one, LinkedIn, GitHub, portfolio, Loom, anything.
Show us 1–3 things you've built that prove you can ship end-to-end.*
Repos, posts, demos, anything. Specifics beat resume bullets.
1500 left
What's a problem you solved with AI as the execution layer, not just chat?*
We care that you reach for AI as a default tool, not occasionally.
1000 left
Show us a product you find beautiful. Why?*
Taste is non-negotiable. We want your real opinions.
800 left
Which AI tools are in your daily workflow?
Pick all you actively use, not just tried.
How much is AI helping you these days?
A sentence or two. Skeptical, force multiplier, in between, where it shines, where it doesn't.
600 left
Share a Claude Code session that shipped a feature end-to-end.
Optional but high-signal. We want to see how you actually work with AI, the prompts, the back-and-forth, the corrections. Whole session, snippet, Loom, gist, anything.
3000 left
When have you most successfully hacked a non-computer system to your advantage?
Optional. Bureaucracy, supply chain, a conference badge, social dynamics, anything. We collect signal here.
1000 left
Most recent role + company
Just the title + company name. We don't need a CV.
200 left
When could you start?
Salary expectation
Confidential. A range is fine.
200 left
Share an actual ComfyUI workflow you're proud of.*
The workflow IS the portfolio. Paste the JSON, link a Gist, link a Loom of you walking through the graph, anything that lets us actually see it. If it ran in production at scale, even better, tell us about the volume + the gnarliest debug it survived. Written-only descriptions are a soft no.
5000 left
Anything else?
Optional. A short note, a question, a relevant detail we missed.
500 left
We commit to a yes / no / not-now within 5 business days. Always. No silent rejections.
Other open roles
Maybe one of these instead.
We hire builders, not roles. If none fit exactly, the open application is at the bottom.
Sentinel·Remote
- global
Help build the AI quality scoring layer Runflow runs in front of every image and video we ship. Hands-on ML, in production tomorrow, at scale.
View role
Infrastructure·Remote
- global
Build the infrastructure that powers the next generation of AI media. GPU fleet, warm workers, queues, FastAPI services, in production tomorrow.
View role
DevRel·Remote
- global
Ship cool things on top of Runflow, bring creators in, drive adoption of the next generation of AI image + video infrastructure.
View role
Open·You define it
Open application
Don't see your role? Tell us what you'd build at Runflow and how it moves the mission forward.
Apply openly