Gen AI Inference Engineer

Job Title: GenAI Inference Engineer (1–2 Years Experience)

Location: Chennai, India

Company: Artcube AI – Pioneers in GenAI for Virtual Product Placement

About Us

We are a next-generation AI company building proprietary models and intelligent algorithms for post-production product placement in TV/OTT and movies. Our GenAI models allow us to seamlessly insert branded products into existing scenes with high realism and contextual fidelity at 4K cinematic quality.

Role Overview

We are looking for a smart, hands-on GenAI Inference Engineer with 1–2 years of experience in Python, shell scripting, and basic DevOps. This role bridges applied machine learning, workflow fine-tuning, and operational stability.

You will:

• Run and manage GenAI inferencing pipelines for image/video content
• Tune model parameters and algorithm settings for specific image/video generation tasks
• Modify visual node-based workflows and Python scripts as needed
• Ensure infrastructure (e.g., GPU machines, storage mounts, environments) is up and running
• Troubleshoot issues across both inference code and deployment layers

Key Responsibilities

• Execute and monitor GenAI inference workflows for product placement pipelines
• Understand the behaviour of different algorithms and fine-tune their parameters for optimal visual output
• Modify shell/Python scripts and visual nodes to adjust the flow of generation tasks
• Maintain and debug deployment environments (e.g., Conda, Docker, GPUs, cron jobs)
• Collaborate with Visual designers and research teams to bridge GenAI outputs with post-production workflows
• Create tools and utilities to streamline inference or enhance productivity

Qualifications

• 1–2 years of professional experience with:
• Exceptional Python programming skills
• Linux shell scripting and basic system operations
• Exposure to Azure or any other cloud environment.

Exposure to any of the following is a plus (Not mandatory):

• Managing and running ML model inference (vision models preferred)
• Diffusion models, vision transformers, or image-to-image generation
• Visual programming platforms (e.g., ComfyUI, Blender)
• GPU setup and troubleshooting (NVIDIA stack, drivers, CUDA)
• Basic DevOps (logging, monitoring, startup scripts, environment setup)

What We Offer

• Opportunity to work on bleeding-edge Visual GenAI tech
• Flexible work environment with a lean, highly skilled team
• An impactful role where you contribute directly to real-world deployments
• Mentorship in advanced video AI understanding and generation workflows

DO NOT UPLOAD UR RESUME HERE, KINDLY COMPLETE THE FORM BELOW AND UPLOAD YOUR RESUME

https://forms.office.com/r/yabb7eA63x?origin=lprLink