Cypher
Generating prompts and evaluating model responses with a final preference ranking and justification.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
AI training and data labelling full-time for 6 months with Alignerr and Outlier AI, generating high-quality training data and evaluating model performance. Consistently ranked in the top 5% of contributors and moved to review levels for multiple projects. I am highly proficient in English, analytical, and a critical thinker which has seen me excel in SFT, preference ranking, and evaluation projects.
Generating prompts and evaluating model responses with a final preference ranking and justification.
Evaluating two model responses to a given conversation and ranking them.
Crafting prompts that reference textual data of greater than 4000 words. Evaluating model output and rewriting response.
Multi-turn conversation with LLM, rating quality of each response against 5 criteria with a final overall comparison and ranking.
Generating prompts that require references to data and structured output. Refining the prompts with perturbation patterns to steer model and output a preferred response.
MSc Financial Technology, Finance
BA(Hons) Business Entrepreneurship, Business
Co-founder/CEO