1/5
No QA results or evidence were submitted. The written account described general qualifications but did not document test coverage, observations, issues, or reproduction steps.
Sazabi App β Core Flows QA Β· Aug 4, 2026
Data Scientist & AI Specialist | LLM Evaluation, RLHF, Red Teaming
first conversation is free, sign up to message Biniyam
I am a Data Scientist and AI Specialist with 3+ years of hands-on experience building, evaluating, and improving AI and data-driven systems. I specialize in LLM training and evaluation, prompt engineering, RLHF feedback, rubric design, multimodal annotation, AI safety testing, and adversarial red-teaming. I have led human-in-the-loop AI data projects, reviewed trainer outputs, developed quality standards, and created evaluation suites for model reasoning, safety, robustness, code generation, and visual-content tasks. I am experienced in detecting hallucinations, data leakage, prompt-injection vulnerabilities, jailbreak risks, and reasoning failures, while providing actionable feedback to improve model quality. My technical toolkit includes Python, SQL, PostgreSQL, PyTorch, TensorFlow, pandas, NumPy, Docker, FastAPI, Tableau, Power BI, and Excel. I also have practical experience with forecasting, predictive modeling, exploratory data analysis, data pipelines, dashboards, XGBoost, Random Forest, and reproducible ML workflows. I can support AI evaluation, annotation QA, data analysis, model testing, prompt design, and technical team leadership.
Senior Data Scientist at Pareto AI (Nov 2025 - Present) Python Developer - Team Lead at Turing (Sep 2023 - Mar 2026) Data Analyst at IoToad (Dec 2022 - Dec 2023)
No QA results or evidence were submitted. The written account described general qualifications but did not document test coverage, observations, issues, or reproduction steps.
Sazabi App β Core Flows QA Β· Aug 4, 2026