Ankush Mishra
Data Scientist @Art - Abstinent Research & Technologies
Signup · Get unlimited contacts
WORK HISTORY
Data Scientist @Art - Abstinent Research & Technologies
Assist in training and fine-tuning LLMs, including data preparation, hyperparameter tuning, and experiment optimization.* Support human-in-the-loop processes, including annotating, reviewing model outputs, and conducting error analysis.* Prepare datasets for supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to improve model behavior.* Evaluate LLM performance using qualitative and quantitative metrics, track issues, and provide improvement recommendations.* Collaborate with researchers to enhance training workflows and optimize LLM models for real-world applications.
EDUCATION
Emerald Heights Higher Secondary School
12th, Mathematics
Emerald Heights Higher Secondary School
10th
Sagar Institute of Science Technology and Engineering (SISTec-E)
Bachelor of Technology - BTech, Computer Science
ABOUT ANKUSH MISHRA
Graduating with a BTech in Computer Science in 2024, my academic journey at SISTec-E laid the foundation for my expertise in data science and advanced technologies. My academic focus on mathematics and computer science cultivated a strong analytical mindset, enabling me to excel in data-driven fields. Presently, I contribute as a Data Scientist at ART - Abstinent Research & Technologies, where I assist in training and fine-tuning large language models (LLMs). My role emphasizes dataset preparation, hyperparameter tuning, and optimizing training workflows. Through collaboration with researchers, I support the real-world application of LLMs by improving model behaviors and conducting comprehensive performance evaluations. My work reflects a commitment to leveraging advanced AI solutions for impactful outcomes.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.