Software Engineer

Summary

Join ResQ, a SaaS-enabled marketplace connecting restaurants with service providers, as a Software Engineer. You will design and build tools using OpenAI and other LLMs, focusing on accurate information retrieval and generation, live audio, and more. Explore and implement the latest AI trends, including multimodal LLMs and agentic RAG systems. Optimize AI model performance for efficiency and scalability. Document your work and mentor junior developers. This role requires a Bachelor's degree in a related field, 3-5 years of software development experience, and at least 6 months of professional or personal focus on AI projects involving LLMs. Experience with Python, LLM frameworks, RAG, vector databases, and multimodal data processing is essential.

Requirements

• Bachelor’s degree in Computer Science, Engineering, or a related field; advanced degrees are advantageous
• 3-5 years of software development experience, with at least 6 months of professional or personal focus on AI projects involving LLMs
• Strong experience in Python with experience in LLM frameworks or libraries
• Experience with RAG or similar LLM augmentation technologies
• Knowledge of vector databases and efficient data retrieval methods for AI
• Hands-on with multimodal data processing (text, image, video)
• Familiarity with cloud services for AI model deployment (not limited to MLOps)
• Knowledge of tools and platforms that integrate AI for end-user applications

Responsibilities

• Design and implement solutions that use OpenAI & other LLMs for providing value to our users, focusing on accurate information retrieval and generation, live audio capabilities, and more
• Explore and implement the latest trends in AI, particularly around multimodal LLMs, agentic RAG systems, and AI-driven search functionalities
• Be knowledgeable about techniques to fine-tune LLMs for specific applications, understanding the nuances of model performance in real-world scenarios
• Stay up to date with advancements like grounding capabilities, agentic RAG, and multimodal RAG (M3DocRAG), applying these to improve our product offerings
• Optimize use AI models audio and text capabilities for efficiency, reducing latency and enhancing scalability in production environments
• Document innovative approaches and share insights with the team to foster a culture of continuous learning
• Address and resolve complex issues related to model performance, integration, and data handling
• Support junior developers in learning about LLMs and related technologies