
Ahmad H
AI and ML Engineer specializing in Python LLM Telegram Bots and RAG Systems
Skills

See my services


Portfolio
Work experience
AI/NLP Research Engineer
Freelancing Career • Self-employed
Sep 2024 - Present • 1 yr 9 mos
Conducting Master's thesis research on URBench — a comprehensive LLM evaluation benchmark for Urdu reasoning. Evaluated 11 models including Qwen3, LLaMA-3.1-70B, DeepSeek, Gemma, and Urdu-specialized models across 5 datasets using zero-shot, few-shot, and chain-of-thought prompting. Built full evaluation pipeline using vLLM on a SLURM cluster. Proposed SDFR-UR — a novel similarity-based dynamic few-shot retrieval method that achieved +6.00pp improvement on GSM8K and +4.94pp on PIQA over CoT baseline. Conducted RAG and cross-lingual prompting experiments with documented failure analysis.
104 Reviews
| (100) | ||
| (4) | ||
| (0) | ||
| (0) | ||
| (0) |
Rating Breakdown
- Seller communication level
- Recommend to a friend
- Service as described
Sort By
tanithecoach

United States
I had a fantastic experience working with this freelancer. Not only did he deliver exactly what I requested with outstanding professionalism, strong attention to detail, and perfect timing, but he also helped me understand a related issue I wasn’t even aware of. That wasn’t part of the initial request,...
$200-$400
Price
3 days
Duration
Seller's Response
george_1235

United States
Great experience! The seller was professional, responsive, and delivered exactly as promised. The quality of work exceeded my expectations, and communication was smooth throughout the process. Highly recommend!
Up to $50
Price
2 days
Duration
Seller's Response

bdzgroup

United States
Great gig and seller
$400-$600
Price
8 days
Duration
Seller's Response
pge68nh

United States
Thank you
$200-$400
Price
4 days
Duration
Seller's Response
mygghy

Romania
Very professional. Excellent communication. I liked it and in the future I will order from him again.
$100-$200
Price
1 day
Duration
Seller's Response