Profile cover
A

AI Inpainting and Object Removal Engineer

Adrian Bergmann

Full-time · Job · New_York

About the role

Object removal sounds like a simple task until the object you're removing is a lamppost in front of a Victorian building and the background needs to reconstruct 40% of the building facade with photorealistic accuracy. Our generative editing platform handles 90,000 edit requests per month from professional photographers, e-commerce teams, and architectural visualization studios. The gap between what they want and what the model delivers is almost always in inpainting quality on complex backgrounds. You'll improve the inpainting and object removal pipeline. The current system uses a diffusion-based inpainting model that performs well on simple backgrounds but struggles with repetitive textures (brick walls, wood grain, fabric), perspective-aware completion (floors, ceilings, structured environments), and semantically coherent background reconstruction for removed objects that cast shadows or occlude important features. The generative engineering team is seven. You'll own the inpainting pipeline, working alongside the model researchers who develop the architectures and the product team who surface quality issues from production usage.

Responsibilities

  • Improve inpainting quality on repetitive textures and structured architectural backgrounds
  • Develop perspective-aware completion for floor and ceiling inpainting scenarios
  • Build semantically coherent shadow removal for edited-out objects
  • Implement quality scoring to detect low-confidence completions before delivery
  • Create evaluation benchmarks covering the specific failure modes from production
  • Optimize inference pipeline for sub-10-second processing on professional-grade images

Requirements

  • 3+ years in computer vision with generative models or image editing experience
  • Hands-on experience with diffusion-based inpainting architectures
  • Strong PyTorch skills with familiarity in image segmentation and masking
  • Understanding of background reconstruction quality criteria
  • Ability to iterate on model behavior based on production failure analysis

Benefits

  • Fully remote with flexible schedule
  • Health, dental, and vision insurance
  • $3,000 annual professional development budget
  • Equity participation
  • Access to high-quality professional photography datasets

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Full-time

Level

Mid-Level

Language

English

Salary Range

$100k – $130k / year

AI Expertise

AI & Machine Learning Engineers data science & analytics

Skills

python pytorch computer vision docker aws numpy

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile