Multimodality
I worked on the RLHF Annotation for image data, in which I used more than 15+ prompt types, and then evaluation two model responses based on the client guidelines. I also worked on Audio SFT and Read Teaming for the models.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
At Turing, you worked as an LLM Trainer from September 2024 to present. Your main responsibilities included evaluating large language model (LLM) outputs for reasoning quality, coherence, and image-text alignment through reinforcement learning from human feedback (RLHF). This experience helped you optimize AI capabilities and provided insights into strategies beneficial for engineering simulations and other data-driven applications
I worked on the RLHF Annotation for image data, in which I used more than 15+ prompt types, and then evaluation two model responses based on the client guidelines. I also worked on Audio SFT and Read Teaming for the models.
Bachelor of Engineering, Engineering
Certificate, Computer and Data Science
Mechanical Design Intern