Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No software listed
No data types listed
No task types listed
Dr. GUPTHA P H Pharm.D | Medical AI Safety & RLHF Specialist +91-9380101762 | [email protected] | Jade, Shivamogga, Karnataka, India PROFESSIONAL SUMMARY Pharm.D graduate specialized in medical LLM safety, RLHF preference modeling, and adversarial red teaming. Expert in evaluating clinical datasets, identifying therapeutic anomalies, and validating language models against evidence-based standards to eliminate clinical hallucinations and secure safety-critical alignment. CORE EXPERTISE ● AI Alignment & RLHF: Clinical Preference Labeling, Adversarial Red Teaming, Multi-turn Prompt Tuning, Hallucination Auditing, Medical RAG Fact-Grounding, Output Bias & Toxicity Mitigation. ● Clinical Pharmacology: Pharmacovigilance, Adverse Drug Reaction (ADR) Safety Audits, Drug-Drug Interaction (DDI) Analysis, Toxicology, Medication Therapy Management (MTM). ● Data & Taxonomies: Clinical Data Management, Medical Coding (ICD-10/CPT), Reference Database Auditing. CLINICAL EXPERIENCE & MODEL ALIGNMENT WORK Clinical Pharmacist Intern | Mandya Institute of Medical Sciences 12/2024 – 12/2025 | Mandya, India Performed high-stakes clinical audits and safety validation within a major multi-specialty hospital, applying the exact verification loops required to align clinical AI agents. ● Adversarial Red Teaming: Evaluated multi-specialty prescriptions to detect and block severe drug-drug interactions, dosage discrepancies, and contraindications—structuring clinical guardrails akin to LLM safety ba
while i am entry level to formal data labeling. I have strong experience in data management, verifying detailed technical and research reports, and utilizing advanced Ai tools for workflow automation.
Pharm D
Clinical pharmacist intern at Mandya Institute of medical sciences
