Skip to main content
Talha TahirTT
Looking for a job

Talha Tahir

@talhatahir1

Senior ML Engineer at 10xEngineers who optimized CUDA image processing for 4K 60 FPS and improved image quality by 10%.

Pakistan
Message

At 10xEngineers, I engineered a CUDA Image Signal Processor pipeline for NVIDIA GPUs and Jetson edge platforms. It improved image quality by 10% and downstream AI model accuracy by 8% while sustaining 4K 60 FPS.

I also designed Quantex, an automated Python and PyTorch quantization framework. It reduced LLM size by up to 20% and Stable Diffusion model size by 25%, within a 1% accuracy drop margin.

Earlier at 10xEngineers, I built edge deployment pipelines and ported YOLOv7 and Moondream to Mojo, achieving inference speedups of 13% and 5%. I also applied structured pruning, knowledge distillation, and quantization to deploy low-latency models on resource-constrained hardware.

On CuQwen, my open-source project, I engineered a C++/CUDA inference engine for low-latency Qwen2.5 execution and developed custom FP16 kernels. My work also includes LLVM code-analysis research at LUMS and an upstream LLDB contribution that added colorized symbol-search output.

Experience

Work history, roles, and key accomplishments

XE
Current

Senior ML Engineer

10xEngineers

Jan 2025 - Present (1 year 10 months)

Engineered a real-time CUDA Image Signal Processor pipeline for NVIDIA GPUs and Jetson platforms, improving image quality by 10% and AI model accuracy by 8% while sustaining 4K 60 FPS. Designed an automated quantization framework in Python/PyTorch, reducing LLM size by up to 20% and Stable Diffusion models by 25% within a 1% accuracy drop margin.

XE

Junior ML Engineer

10xEngineers

Jan 2023 - Jan 2025 (2 years)

Built deployment pipelines for edge hardware, porting YOLOv7 and Moondream models to Mojo with memory optimization and custom GPU kernels, achieving 13% and 5% inference speedups. Applied structured pruning, knowledge distillation, and quantization to deploy low-latency models on resource-constrained hardware.

Model Optimization
Edge Deployment
YOLOv7
Moondream
Mojo
GPU Kernel Programming
Structured Pruning
Knowledge DistillationQuantization
LU

Research Assistant

LUMS

Jan 2022 - Jan 2023 (1 year)

Conducted static and dynamic code analysis using custom LLVM passes, contributing to a tier-1 research publication. Upgraded static analysis infrastructure, cutting false positive rates by 15% through stream optimization.

Education

Degrees, certifications, and relevant coursework

Lahore University of Management Sciences logoLS

Lahore University of Management Sciences

Bachelor of Science, Computer Science

2019 - 2023

B.S. in Computer Science from Lahore University of Management Sciences (LUMS) from 2019 to 2023.

Tech stack

Software and tools used professionally

Availability

Looking for a job

Location

Pakistan

Authorized to work in

Salary expectations

60k+ USD

Interested in hiring Talha?

You can contact Talha and 600K+ other talented remote workers on Himalayas.

Message Talha

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan