Back to LeaderboardLast snapshot: Sep 9
Devanshu S.
Badge

Devanshu S.

AI Data Annotation | LLM Evaluation | Model Comparison

Hi, Iโ€™m a Top Rated Plus freelancer from India with a 100% Job Success Score on Upwork. I specialize in AI data annotation, LLM evaluation, and model comparison, focused on improving the quality, accuracy, and usefulness of AI-generated responses. I actively keep learning and adapting to evolving AI systems and evaluation standards, so my work stays aligned with current expectations. I can work comfortably in both English and Hindi, depending on the project requirements. โญ Top Rated Plus Freelancer โœ… 100% Job Success Score ๐Ÿ‘ค What I Do ๐Ÿ”น Creating structured prompts based on guidelines ๐Ÿ”น Comparing responses from multiple AI models (A/B evaluation) ๐Ÿ”น Selecting the better response with clear reasoning ๐Ÿ”น Checking factual accuracy and instruction-following ๐Ÿ”น Evaluating tone, clarity, and usefulness ๐Ÿค– Core Skills ๐Ÿ”น Data annotation & labeling (text and image-based) ๐Ÿ”น AI response comparison & evaluation ๐Ÿ”น Fact-checking and accuracy verification ๐Ÿ”น Writing clear and consistent reasoning ๐Ÿ”น Quality review and strict guideline adherence ๐Ÿ” Quality & Review ๐Ÿ”น Reviewing and improving work from other annotators ๐Ÿ”น Fixing inconsistencies and maintaining high standards ๐Ÿ”น Ensuring outputs meet expected quality benchmarks ๐Ÿ”น Maintaining consistency across large datasets โš™๏ธ How I Work ๐Ÿ”น Quick adaptation to new guidelines and workflows ๐Ÿ”น Strong focus on detail and consistency ๐Ÿ”น Comfortable with high-volume and repetitive tasks ๐Ÿ”น Logical, structured decision-making (no guesswork) ๐Ÿง  Experience Highlights ๐Ÿ”น AI response comparison and ranking tasks ๐Ÿ”น Structured evaluation using rating systems ๐Ÿ”น Prompt-based evaluation workflows ๐Ÿ”น Large-scale annotation projects ๐ŸŽฏ Why Clients Choose Me ๐Ÿ”น Accuracy over speed ๐Ÿ”น Clear and consistent reasoning ๐Ÿ”น Strong instruction-following ๐Ÿ”น Reliable and predictable output quality ๐Ÿ“ฉ Letโ€™s Work If youโ€™re looking for reliable support in AI data annotation, LLM evaluation, or model comparison, Iโ€™m ready to contribute with consistency and clarity.

๐Ÿ‡ฎ๐Ÿ‡ณNew Delhi, India$30/hr100% JSS3.11 (34)Since Oct 2017
MRR
$3,794
๐ŸŒ#8,787/363K
๐Ÿ‡ฎ๐Ÿ‡ณ#1,102/40.5K
Recent Earnings
$22,764
๐ŸŒ#8,787/363K
๐Ÿ‡ฎ๐Ÿ‡ณ#1,102/40.5K
Total Earnings
$87,630
๐ŸŒ#42.3K/363K
๐Ÿ‡ฎ๐Ÿ‡ณ#6,717/40.5K
Avg. Per Project
$1,753
๐ŸŒ#78.8K/363K
๐Ÿ‡ฎ๐Ÿ‡ณ#9,655/40.5K
Recent Projects
2
1f1h
๐ŸŒ#57.0K/363K
๐Ÿ‡ฎ๐Ÿ‡ณ#9,288/40.5K
Total Projects
50
50f16h
๐ŸŒ#57.0K/363K
๐Ÿ‡ฎ๐Ÿ‡ณ#9,288/40.5K
MRR Performance Over Time
$50k$25k$0
6 mo ago3 mo agoNow
Coming SoonGathering historical data
World Skill Rankings
of 63
#1
Image Prompt EngineeringTop <0.01%
#1Model Training Prompt Engineering
#1Instruction-Based Prompt
#1Text Classification
#2Hindi
#2Sentiment Analysis
#5AI Fact-Checking
#6Data Labeling
#7ChatGPT Prompt
#7Generative AI Prompt
#10Data Annotation
#16Generative AI Prompt Engineering
#17Content Moderation
#18Quality Control
#20AI Content Editing
#25Data Collection
#28AI Model Training
#92AI Model Integration
#94Prompt Engineering
#137LLM Prompt Engineering
๐Ÿ‡ฎ๐Ÿ‡ณIndia Skill Rankings
of 69
#1
Data LabelingTop <0.01%
#1Image Prompt Engineering
#1Model Training Prompt Engineering
#1Generative AI Prompt
#1Quality Control
#1Instruction-Based Prompt
#1Text Classification
#1Sentiment Analysis
#2Hindi
#2AI Fact-Checking
#2Content Moderation
#3AI Content Editing
#3Data Annotation
#3ChatGPT Prompt
#4Generative AI Prompt Engineering
#5Data Collection
#6AI Model Training
#15Prompt Engineering
#17AI Model Integration
#34LLM Prompt Engineering
Devanshu S. โ€” Top 3% in India | UpworkMRR