Open to opportunities

Tejas Mohare

@tejasmohare

AI Evaluation Specialist and Trainer focused on safer, more reliable LLM outputs through rigorous benchmarking and feedback.

India

Message

What I'm looking for

I’m looking for remote opportunities where I can evaluate and improve LLM output quality—benchmarking, hallucination detection, safety testing, and structured feedback—while working with detailed guidelines and teams focused on accuracy and alignment.

I’m an AI Evaluation Specialist, AI Trainer, and Data Annotation Expert with experience across Mercor, Alignerr, Outlier, and Mindrift. I evaluate AI-generated outputs across reasoning, coding, instruction-following, and conversational tasks using structured guidelines to improve reliability and alignment.

My work includes RLHF evaluation, response ranking, factuality validation, hallucination detection, and AI safety reviews. I identify quality issues, edge cases, inconsistencies, and model failures, then deliver detailed, actionable feedback to strengthen model performance.

I also contribute to LLM evaluation workflows by reviewing, ranking, and benchmarking responses, performing truthfulness validation, and supporting AI red teaming and quality assessment workflows. I’m comfortable maintaining high standards, following detailed instructions, and collaborating remotely with strong written English and analytical reasoning.

Experience

Work history, roles, and key accomplishments

LLM Evaluation Specialist

Alignerr

Reviewed, ranked, and benchmarked LLM responses using detailed evaluation guidelines, including annotation, truthfulness validation, and quality assessment workflows. Supported large-scale training pipelines through structured evaluation, red teaming, and feedback on edge cases and failures.

LLM Evaluation Data Annotation Response Ranking Benchmarking Truthfulness Validation AI Red Teaming

AI Analyst / Trainer

Mercor

Evaluated AI outputs across reasoning, coding, instruction-following, and conversational tasks, performing RLHF evaluation, response ranking, factuality validation, hallucination detection, and AI safety reviews. Delivered structured, guideline-based feedback to improve model reliability, accuracy, and alignment.

AI Output Evaluation Response Ranking Hallucination Detection AI Safety Testing Instruction Following Quality Assurance

LLM Evaluation Specialist

Mindrift

Reviewed and ranked AI outputs using established evaluation guidelines, conducting benchmarking, annotation, and truthfulness validation. Performed AI safety testing, including red teaming, and contributed to training data quality through detailed, structured feedback.

AI Benchmarking LLM Evaluation Data Annotation AI Safety Testing AI Red Teaming Response Ranking Truthfulness Validation Quality Assurance

LLM Evaluation Specialist

Outlier

Evaluated and benchmarked AI-generated responses by following detailed rubrics, including annotation, prompt analysis, truthfulness checks, and quality scoring. Identified edge cases and inconsistencies and provided structured feedback to improve model performance and safety.

LLM Evaluation Data Annotation Truthfulness Validation Quality Assessment Response Ranking Hallucination Detection