Kagapu Adityavardhan

AI Researcher

Andhra Pradesh, India6 mos experience

Key Highlights

Passionate problem solver with strong analytical skills.
Experience in developing multi-agent systems and optimizing LLMs.
Eager to contribute to innovative data-driven solutions.

Stackforce AI infers this person is a Data Science and AI enthusiast with a focus on quantitative finance and software development.

Contact

Skills

Core Skills

Data ScienceMachine Learning

Other Skills

C (Programming Language)C++CommunicationCompetitive programmingDeep LearningLanggraphLarge Language ModelsMathematicsMetrics evaluationMulti-agent systemsNatural Language Processing (NLP)Python (Programming Language)Reinforcement LearningSoftware DevelopmentSupervised fine-tuning

About

I’m Aditya, a passionate problem solver with a strong love for mathematics and analytical thinking. My interests lie in tackling complex challenges, particularly in the fields of quantitative finance, software development, and data science . I aspire to work in a company that values talent, innovation, and merit above all else. Currently, I am in the learning phase, continuously expanding my skill set and gaining hands-on experience to build a solid foundation for my career. I am eager to contribute to dynamic teams where I can apply my skills, grow as a professional, and create meaningful impact through data-driven and innovative solutions. Let’s connect!

Experience

Walmart global tech india

Data Science Intern

May 2025 – Jul 2025 · 2 mos · On-site

I developed a multi-agent system and worked on evaluating the agents and comparing their trajectories using various metrics.
monitoring the agent work flow using Phoenix

Data ScienceMulti-agent systemsMetrics evaluation

Turing

LLM Trainer

Nov 2024 – Dec 2024 · 1 mo · Remote

Proficient in optimizing Large Language Models (LLMs) through Reinforcement Learning with Human Feedback (RLHF) and supervised fine-tuning. Skilled in designing and curating challenging mathematical problem sets to enhance model performance and reasoning capabilities.

Large Language ModelsReinforcement LearningSupervised fine-tuningMachine Learning