NLP Generative AI - Multi-modal & RAG Chatbots - Research and Implementation with LLMs

About XA Group:

At XA Group, we are dedicated to driving substantial technological advancements in the automotive and insurance sectors. Our mission is to empower businesses with intelligent solutions, making them smarter, safer, and more efficient.

Key Responsibilities:

• • 1. Image and Text-Based Chatbot:
    • · Research and implement a chatbot that can seamlessly integrate images and text using state-of-the-art LLMs such as GPT-4V and LLaVa.
    • · Ability to used embeddings from CLIP or similar to make image-text understanding better. (Fine-tune them as needed)
    • 2. Text to Image (Video) Generation:
    • · Explore and implement models for generating images or videos from textual descriptions.
    • · Develop practical applications with respect to data storytelling, such as generating kids' story illustrations from custom input data.
    • · Focus on working with diffusers and evaluate their impact on the quality and diversity of generated content.
    • 3. Fine-tune LLM Models specific to multi-modality:
    • · Implement fine-tuning strategies for LLMs to generate content specific to the domain. Create instruct datasets for the same.
    • · Showcase the model's ability to understand and respond to instruction within the specified domain context.
    • 4. Model Quantization:
    • · Investigate model quantization techniques to optimize inference speed and accuracy, particularly on GPUs.
    • · Conduct experiments to demonstrate the trade-offs between quantization levels and model performance.
    • 5. Model Evaluation and Metrics:
    • · Develop comprehensive evaluation metrics for the image and text-based chatbot, as well as the text-to-image (video) generation models.
    • · Present findings through clear and concise reports, including visualizations and comparisons.

Requirements:

• • · Background in Generative AI, Natural Language Processing (NLP) and machine learning.
    • · Proficiency in programming languages such as Python and familiarity with relevant libraries (e.g., TensorFlow, PyTorch). Worked with LLMs, hugging face transformers.
    • · Strong analytical and research skills.
    • · Effective communication skills, including the ability to present findings to stakeholders.
    • · Ability to work independently and as part of a team

Perks:

• • Mentorship from industry experts in the field of Computer Vision.
    • Hands-on experience with cutting-edge technologies and real-world applications.
    • Opportunity to contribute to projects with meaningful impact.
    • Collaborative and innovative work environment.

$800 - $1,000 a month

Apply for this job