2 Generative Ai Engineer Mumbai

## About the Role One of our AI products built by us last year is now used by 9 million users every month! And we are hiring! As a GenAI Engineer, You are expected to have at least 1 year of coding experience in the latest Gen AI, specializing in open-source diffusion image models (e.g., Flux-Klein family), video generation models (such as LTX-2), and associated tooling (e.g., ComfyUI, LoRA training, etc.). Your role will be instrumental in all the business areas of the company which spans over $10+ Billion GTV in the real-estate sector in India and abroad. You will be working on innovative AI applications at the monthly million user scale. You are expected to be on top of all AI developments in the world on a daily basis and ideating suitable usecases for the company. You will be reporting directly to the Head of AI at Square Yards. ## Responsibilities - Ideate, Design, Develop, and Implement: Create end-to-end image and video generation pipelines using diffusion models. This includes data sourcing/curation, training LoRAs, prompting, integration, evaluation, and deployment. - Diffusion Model Expertise: Implement and deploy a wide range of open-source diffusion models, including Flux Klein and Qwen Image. Experience with conditioning mechanisms like Inpainting, ControlNets, and IPAdapters is crucial. - Workflow Orchestration & Automation: Design, build, and optimize image generation workflows using ComfyUI. Develop and maintain programmatic wrappers and integrations for these ComfyUI workflows. - Video Generation Model Implementation: Develop and implement solutions using latest open-source and experimental video generation models such as LTX-2 and WAN Animate. - Closed-Source Model Exploration: Experiment with and evaluate leading closed-source image and video models like Google Nanobanana, Kling, Veo2/3, and Seedance, identifying potential integration points or comparative advantages. - Model & Platform Ownership: Take primary ownership of managing open-source models and frameworks. Stay updated on APIs from major AI providers for potential complementary use. - Basic LLM Application: Possess a foundational understanding of Large Language Models (LLMs) and their APIs for tasks like advanced prompt engineering, image captioning, or multimodal applications supporting image/video generation pipelines. - Cross-Functional Collaboration: Work closely with product managers and software engineers to integrate image/video generation capabilities into user-facing products and internal systems. - Documentation & Best Practices: Maintain comprehensive documentation for models, fine-tuning processes, ComfyUI workflows, experiments, and deployment processes. Adhere to MLOps best practices for generative models. ## Skills & Qualifications - **Education**: Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related quantitative field. - **Programming**: Expert-level Python proficiency and strong experience with relevant libraries. ### Diffusion & Video Generation Stack - **Diffusion Models**: Demonstrable experience working with FLUX (Klein) and LTX-2 models, fine-tuning, and related frameworks. - **LLMs**: Deep understanding and practical experience with various LLMs and their APIs. - **API Integration**: Experience consuming and integrating APIs from major AI providers. ### Problem-Solving - Excellent analytical and problem-solving abilities with meticulous attention to detail, especially in visual quality and model behavior. ### Adaptability - Proven ability to learn quickly, work independently, and adapt to new technologies and research advancements in the AI image/video synthesis field. ### Communication - Strong verbal and written communication skills, enabling effective collaboration with technical and non-technical stakeholders. ## Bonus Points - You have video generation projects (e.g., complex ComfyUI workflows, novel applications of diffusion models). - Experience with generating videos using LTX-2. - Contributions to open-source GenAI projects. - Experience with 3D asset generation or integration with visual content.