Beschreibung

AI evaluator and researcher with experience in human-in-the-loop AI workflows, LLM evaluation, data analysis, and technical research. Skilled in assessing AI-generated outputs for accuracy, reasoning quality, alignment, and consistency using structured evaluation frameworks. Background spans software engineering, systems thinking, research-driven problem solving, and emerging AI applications in spacetech and engineering domains. Comfortable collaborating remotely on technical AI evaluation, annotation, and model improvement tasks.

Branchenexpertise

Sprachen

Englisch
Muttersprachlich oder zweisprachig
Punjabi
Muttersprachlich oder zweisprachig
Deutsch
Grundkenntnisse

Arbeitsortpräferenzen

Vor Ort möglich

Graz (bis zu 50 km)

Alignerr
Human-in-loop AI evaluator
Januar 2026 - Heute (5 Monate)
Evaluated and improved AI model outputs through structured human feedback tasks, including rating, labeling, classification, fact-checking, and response quality assessment. Followed detailed evaluation guidelines and rubrics to ensure high-quality, consistent data for training large AI systems. Worked across text, image, and multimodal content while maintaining accuracy, analytical reasoning, and attention to detail in a remote freelance environment.
Machine learning data annotation artificial intelligence analytical reasoning LLM
BFAIR Project, World Bank
IT Consultant
August 2024 - Oktober 2024 (2 Monate)
Designed and modeled a comprehensive Public Investment Management (PIM) system; developed mermaid system-architecture diagrams and UX mockups. Authored a concept note appraising digital-education infras tructure for government schools in Punjab, India.
Research
Data Scientist
Januar 2021 - Heute (5 Jahre und 5 Monate)
Python-based predictive modeling and machine learning mission and research projects related spacetech