Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
LabelboxMercorTolokaNo subject matter listed
Computer Code Programming
TextWith over six years of experience as a software and AI engineer, I have worked extensively on building and optimizing data pipelines, training datasets, and evaluation protocols for large language models (LLMs) in production environments. My expertise spans data labeling, annotation, and benchmarking, particularly in projects involving RLHF (Reinforcement Learning from Human Feedback), LLM optimization, and real-world evaluation using tools like SWE-bench. I have hands-on experience developing and curating datasets, defining annotation guidelines, and collaborating with cross-functional teams to ensure high-quality, reliable training data for NLP and AI systems. My technical toolkit includes Python, Pytorch, LangChain, OpenAI API, and various cloud platforms, and I have contributed to domains such as healthcare, identity verification, and voice-based AI assistants, where accurate data annotation and robust evaluation are critical to system performance and compliance. I am passionate about building scalable, maintainable solutions that enhance AI model reliability and user experience.
I’ve Contributed to Gemini’s RLHF pipeline, aligning model outputs with user expectations and focusing on RLHF to align the model's outputs with user expectations and improve usability
Bachelor of Science, Computer Science
Senior AI/LLM Engineer
Fullstack AI Engineer
