Mobile AI Inference Engineer (Vulkan, LoRA, Quantization)

Framework Ventures

Full-time Engineering
Apply Now
Location
karachi division, sindh, Pakistan
Posted
June 04, 2026

Job Description

Framework Ventures is looking for an experienced AI Model Engineer in Pakistan. The role involves optimizing and implementing inference and fine-tuning kernels for language models focusing on GPU acceleration using Vulkan. Strong proficiency in C++ and expertise in GPU programming are required. Candidates should have experience with mixed-precision model optimization and mobile GPU acceleration. This position provides an opportunity to work with cross-functional teams to deliver efficient language model deployments for edge and mobile applications.
#J-18808-Ljbffr