Hidden

LLM Engineer for Advanced Sports Analytics Project

As an NLP Specialist, your main responsibility will be to develop and fine-tune NLP algorithms that convert user-generated natural language into structured JSON formats and vice versa. This includes integrating and utilizing detailed fitness datasets to tailor workout suggestions according to users' specific needs, such as injuries and physical capabilities. You will also create a dynamic content generation system that modifies workouts based on user input and generates comprehensible summaries of these workouts.

Моя компания специализируется на разработке мобильных приложений и ML решений на заказ, преимущественно для рынка США. У ребят из команды есть опыт работы в Google, Сбере и других больших технологических компаниях, а у компании разработки приложений как для успешных стартапов, так и для устоявшихся компаний. У нас положительный опыт найма и сотрудничества с коллегами из чата. Сейчас у нашего партнера, HiQ Fitness, для которого мы активно ведем разработку, открыты две вакансии: AI Engineer и LLM Engineer в проекте по спортивной аналитике. Есть возможность работы как через мою компанию так и напрямую.

HiQ Fitness is on a mission to utilize truly sophisticated and rigorous artificial intelligence to accelerate the pace of improvement in athletic performance. In short, athletes who use our technology will ‘Get Better Faster’ and unlock a powerful competitive edge that has never been available.

• Modify bedrock LLMs to accurately interpret and generate natural language descriptions of CrossFit workouts, translating these descriptions into an in-house data structure (JSON format) and summarize structured workouts in natural language.
• Implement a robust feedback loop within the interface to allow users to modify workouts based on personal preferences or requirements, ensuring these modifications are reflected accurately in the system’s output.
• Utilize available datasets to enforce completeness and correctness in workout descriptions, prompting users for missing information and ensuring all necessary workout components are included.
• Develop algorithms to suggest workout modifications that accommodate user injuries, physical limitations, fitness goals, or equipment availability regarding movement types and required body mechanics.
• Create models to scale workout difficulty appropriately, using data on movement difficulty hierarchies and user performance history to adapt workouts while maintaining intended stimuli.
• Collaborate with data scientists and engineers to ensure seamless integration of external datasets into the LLM, enhancing its contextual understanding and output relevance.

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Computational Linguistics, or a related field.
• Strong proficiency in natural language processing and understanding, with experience in fine-tuning LLMs like ChatGPT, Llama, Mistral, Claude, etc.
• Prior working examples of direct experience with LLM fine-tuning, RAG, and LangChain style LLM workflows that trigger application logic (i.e. GPT Functions).
• Demonstrated ability in working with JSON data structures and dynamic content generation based on user interactions.
• Experience with dataset integration and application in machine learning models, especially for personalized content generation.
• Knowledge of along with passion for fitness and workout structures, particularly in CrossFit.
• The ideal candidate will be an active CrossFit Athlete who takes classes in a CrossFit box at least 3 times per week and possess a deep understanding and appreciation for CrossFit workout paradigms and movements.
• Proficient in programming languages used in AI and machine learning development, such as Python, and familiar with AI development tools and platforms.
• Excellent problem-solving skills, with a capacity to work on complex challenges requiring innovative solutions.
• Completely fluent and comfortable working in English
• Strong communication and documentation skills, capable of working collaboratively in a multidisciplinary team to translate complex product requirements into actionable development plans.
• Experienced, capable, & successful; but shows up each day as genuinely humble, collaborative, and eager to learn.
• Strong problem-solving skills.
• The ideal candidate will also have a broad, applied Data Science skillset that can be used (either directly or as a mentor or, if qualified, a manager to others on the team) to tackle the many other data science problems we plan to tackle outside of the ‘movement recognition’ project.
• Standard predictive modeling techniques (Regression, etc.)
• Time series and sequence based models
• Deep Learning Algorithms

Бонусы длительного сотрудничества с моей компанией:

• Помощь в создании и продвижении профиля на Upwork.
• Рост часовой ставки со стажем.
• Возможность перехода на full-time позицию.