AI Model Optimization Engineer for Mobile and Edge Use Cases
2 days ago
Job Overview
Tether is revolutionizing digital finance by harnessing blockchain technology to enable instant, secure, and global transactions at a fraction of the cost.
The company empowers businesses to seamlessly integrate reserve-backed tokens across blockchains, driving sustainable growth through innovative product solutions.
Key Initiatives- Tether Finance: Developing trusted stablecoins like USDT, relied upon by hundreds of millions worldwide.
- Tether Power: Optimizing excess power for Bitcoin mining using eco-friendly practices.
- Tether Data: Fueling breakthroughs in AI and peer-to-peer technology, reducing infrastructure costs and enhancing global communications.
- Tether Education: Democratizing access to top-tier digital learning, empowering individuals to thrive in the digital and gig economies.
About the Role
We seek an experienced AI Model Engineer with deep expertise in kernel development, model optimization, fine-tuning, and GPU acceleration. The engineer will extend the inference framework to support inference and fine-tuning for Language models with a strong focus on mobile and integrated GPU acceleration (Vulkan).
Responsibilities- Implement and optimize custom inference and fine-tuning kernels for small and large language models across multiple hardware backends.
- Implement and optimize full and LoRA fine-tuning for small and large language models across multiple hardware backends.
- Design and extend datatype and precision support (int, float, mixed precision, ternary QTypes, etc.).
- Design, customize, and optimize Vulkan compute shaders for quantized operators and fine-tuning workflows.
- Investigate and resolve GPU acceleration issues on Vulkan and integrated/mobile GPUs.
- Architect and prepare support for advanced quantization techniques to improve efficiency and memory usage.
- Debug and optimize GPU operators (e.g., int8, fp16, fp4, ternary).
- Integrate and validate quantization workflows for training and inference.
- Conduct evaluation and benchmarking (e.g., perplexity testing, fine-tuned adapter performance).
- Conduct GPU testing across desktop and mobile devices.
- Collaborate with research and engineering teams to prototype, benchmark, and scale new model optimization methods.
- Deliver production-grade, efficient language model deployment for mobile and edge use cases.
- Work closely with cross-functional teams to integrate optimized serving and inference frameworks into production pipelines designed for edge and on-device applications.
Requirements
- Proficiency in C++ and GPU kernel programming.
- Proven Expertise in GPU acceleration with Vulkan framework.
- Strong background in quantization and mixed-precision model optimization.
- Experience and Expertise in Vulkan compute shader development and customization.
- Familiarity with LoRA fine-tuning and parameter-efficient training methods.
- Ability to debug GPU-specific performance and stability issues on desktop and mobile devices.
- Hands-on experience with mobile GPU acceleration and model inference.
- Familiarity with large language model architectures (e.g., Qwen, Gemma, LLaMA, Falcon etc.).
- Experience implementing custom backward operators for fine-tuning.
- Experience creating and curating custom datasets for style transfer and domain-specific fine-tuning.
- Demonstrated ability to apply empirical research to overcome challenges in model development.
-
Expert Language Model Optimizer
2 days ago
Hyderabad City Taluka, Pakistan beBeeQuantization Full time $150,000 - $175,000Job OverviewAs a senior AI model engineer, you will play a key role in enhancing our inference framework to support language models on mobile and integrated GPU acceleration. This involves extending the existing framework to optimize performance and efficiency for various hardware backends.ResponsibilitiesImplement and optimize custom inference and...
-
Advanced AI Model Developer
2 days ago
Quetta City Tehsil, Pakistan beBeeEngineer Full time $200,000 - $250,000Job OverviewWe are revolutionizing digital finance by crafting innovative solutions that empower businesses to seamlessly integrate reserve-backed tokens across various blockchain platforms.Innovate with Us:Tether Finance: Our cutting-edge product suite features the world's most trusted stablecoin, USDT, relied upon by hundreds of millions worldwide.Our...
-
AI System Reliability Engineer
2 days ago
Peshawar City Tehsil, Pakistan beBeeEngineering Full time $120,000 - $180,000About the RoleWe are seeking a seasoned Engineering Manager to lead a team focused on ensuring the reliability, robustness and performance of AI features in production environments.You will be responsible for building and growing a high-performing team of engineers and analysts focused on data analysis, debugging, root-causing production issues and...
-
Faisalabad City Tehsil, Pakistan beBeeModeling Full time $150,000 - $190,000About Our AI Model Engineer RoleWe're seeking a seasoned professional with in-depth knowledge of kernel development, model optimization, fine-tuning, and GPU acceleration.This position demands hands-on experience with quantization techniques, LoRA architectures, Vulkan backend, and mobile GPU debugging.
-
AI Engineer
1 week ago
Peshawar, Khyber Pakhtunkhwa, Pakistan Zypher Enterprise Private Limited Full time $30,000 - $150,000 per yearOverviewWe are hiring an AI Engineer to work on computer vision, object detection, behavior analysis, and deep learning systems. You will design, train, and deploy AI models, integrate them into real-world applications, and collaborate with our engineering team to build intelligent, scalable products.Key ResponsibilitiesDevelop AI/ML models for computer...
-
Senior Model Architect
2 days ago
Bahawalpur City Tehsil, Pakistan beBeeMachineLearning Full time $100,000 - $160,000Job Title: Lead Architect for AI Model Development">As a core member of our AI model development team, you will spearhead innovation in architecture design for cutting-edge models of various scales.You will have a deep expertise in video generation model architectures with a hands-on, research-driven approach.Your mission is to explore and implement novel...
-
Bahawalpur City Tehsil, Pakistan beBeeArtificialintelligence Full time 12,000,000 - 15,000,000About the RoleWe are seeking an exceptional AI developer to join our team in developing innovative AI solutions for fleet safety. As a key member of our R&D team, you will be responsible for designing and deploying cutting-edge models using advanced algorithms and machine learning techniques.This role offers an exciting opportunity to work on complex...
-
Peshawar City Tehsil, Pakistan Motive Full timeOverviewMotive empowers the people who run physical operations with tools to make their work safer, more productive, and more profitable. For the first time ever, safety, operations and finance teams can manage their drivers, vehicles, equipment, and fleet related spend in a single system. Combined with industry leading AI, the Motive platform gives you...
-
AI Development Specialist
2 days ago
Peshawar City Tehsil, Pakistan beBeeArtificial Full time $80,000 - $150,000**Job Opportunity: AI Engineer**This is an exceptional opportunity to work with a talented team in the development of cutting-edge artificial intelligence solutions. The ideal candidate will have a strong foundation in machine learning algorithms and technologies.The selected individual will be responsible for designing, implementing, and optimizing AI...
-
Senior AI Reliability Lead
2 days ago
Faisalabad City Tehsil, Pakistan beBeeEngineering Full time $150,000 - $250,000About MotiveMotive empowers people running operations with tools to make work safer, more productive and profitable.The company serves over 100,000 customers across industries. It combines industry-leading AI with a single system for managing drivers, vehicles, equipment, and fleet-related spend.About the RoleLead experienced engineers in data analysis,...
