Location : ,
Title: Software Engineer (Large Language Models)
|
Responsibilities o Seamlessly integrate and fine-tune state-of-the-art LLM models for optimal performance on our specific hardware configurations. o Continuously evaluate and implement the latest LLM advancements to ensure our solution remains at the forefront of technology. o Design and build robust, scalable APIs that expose LLM functionalities for seamless integration with various hardware components and software applications across our ecosystem. o Ensure APIs are well-documented, easily maintainable, and adhere to industry best practices. • Backend Infrastructure: o Create and maintain data pipelines for collecting, processing, and analyzing user data to enhance LLM model performance and deliver personalized user experiences. • Documentation: Maintain clear and concise documentation of code, architecture, and LLM integration processes.
Qualifications • 3+ years of experience in software development with demonstrated experience in integrating AI/ML models, ideally in a hardware-centric environment. • Proficiency in Python (backend) or other relevant programming languages for machine learning. • Experience working with LLM APIs and libraries (e.g., OpenAI API, LangChain). • Demonstrated ability to optimize LLM models for specific hardware constraints (e.g., memory, processing power). • Deep understanding of how to effectively integrate and leverage LLM models within a software ecosystem. • Experience in designing and building RESTful APIs that are scalable, secure, and easy to use. • Proficiency in data processing, analysis, and pipeline development using tools like Apache Spark or similar technologies. RAG (Retrieval Augmented Generation) JavaScript UI/UX YAML
Preferred Qualifications • Familiarity with natural language processing (NLP) techniques. • Contributions to open-source projects or publications in relevant fields. • Experience with integration platforms like Mulesoft. • Familiarity with Azure cloud services and OpenAI's API.
|