Computer Vision Engineer – Generative AI

This role is for one of our clientsIndustry: Technology, Information and MediaSeniority level: Mid-Senior levelMin Experience: 3 yearsJobType: full-time

About The Role

We are looking for a

highly skilled Computer Vision Engineer

with deep expertise in

Generative AI

to join our cutting-edge visual computing team. In this role, you’ll design and deploy AI-driven systems that enable photorealistic image generation, object placement, and scene modification—transforming how users visualize furniture in real-world environments. This is an opportunity to build next-gen visual intelligence tools using the latest in diffusion models, rendering pipelines, and large-scale AI systems.

Key Responsibilities

🎨

Generative Vision Modeling

Develop and refine

diffusion-based generative models

for tasks including object insertion, transformation, and high-resolution rendering.Solve challenges in

furniture placement, replacement, and scene consistency

, delivering ultra-realistic outputs across diverse environments.🔬

AI Research & Implementation

Stay at the forefront of visual AI—implementing novel architectures in

Stable Diffusion, DDPM, NeRF, GANs

, or transformer-based generation.Translate state-of-the-art research into production-grade models optimized for speed and accuracy.🧠

Model Development & Deployment

Architect, train, and deploy scalable models using

PyTorch

and GPU-accelerated workflows.Optimize pipelines for real-time inference, memory efficiency, and photorealistic rendering.🔁

Collaboration & Integration

Work cross-functionally with design, product, and engineering teams to develop AI features that enhance user experience.Collaborate with DevOps to package and serve models via APIs and microservices in live environments.

Technical Requirements

✅

Core Expertise

3–8 years of experience in

Computer Vision

,

Deep Learning

, or

Generative AI

.Proven experience working on

image generation, object detection, and replacement

with generative techniques.Mastery in

PyTorch

, with deep understanding of

diffusion models

and training paradigms.🔧

Toolset & Frameworks

Hands-on experience with

Stable Diffusion

,

GANs

,

NeRF

, or similar architectures.Strong understanding of

3D rendering pipelines

, including lighting, shading, and texture mapping.Proficiency in

CUDA

for accelerated model training and deployment.

📊 Additional Skills

Experience with

large datasets

, preprocessing, and augmentation techniques.Background in

image synthesis

,

segmentation

, or

scene understanding

is a plus.

Soft Skills & Mindset

Strong problem-solving abilities with a research-meets-product mindset.Ability to communicate complex concepts clearly and effectively to technical and non-technical teams.Team-first attitude with a drive to experiment, innovate, and iterate fast.

Tech Keywords

Diffusion Models

• Generative AI
• PyTorch
• Stable Diffusion
• NeRF
• GANs
• Computer Vision
• Photorealistic Rendering
• CUDA
• Object Placement
• 3D Vision
• Image Synthesis