ML Optimization Engineer - Gonka Network Mining Operations

About Us:

We are a leading participant in the Gonka decentralized AI network (https://gonka.ai/), leveraging high-performance GPU infrastructure to maximize mining rewards. We’re seeking an ML Optimization Engineer to help us achieve superior efficiency and weight in the Gonka ecosystem.
 

Key Responsibilities:

• Implement advanced inference optimizations (speculative decoding, quantization, attention modifications, etc.) to maximize mining weight — techniques already proven to achieve double weight with identical GPUs by other participants
• Fine-tune Docker configurations for various GPU models based on available registry
• Develop custom optimization strategies that balance throughput and quality
• Create and maintain custom Docker images optimized for specific GPU architectures
• Design and implement systems for stable and scalable mining of Gonka and other protocols
• Develop optimized images for Tenstorrent AI ASICs to expand our hardware ecosystem beyond current GPU deployment
• Migrate Python code and VLLM implementations to new VLLM images and adapt them for specific GPU cards
   

Required Qualifications:

• Proven experience with large language model optimization techniques
• Strong understanding of transformer architectures and attention mechanisms
• Proficiency with PyTorch, CUDA, and GPU optimization techniques
• Experience with vLLM, FlashInfer, or similar inference optimization frameworks
• Familiarity with Docker containerization and GPU workload management
   

Preferred Qualifications:

• Experience with Claude Code Max (will be provided if needed)
• Previous experience with Gonka or similar decentralized AI networks
• Background in competitive ML or distributed systems optimization
• Experience with NVIDIA GPU architectures (B200/B300/H200/H100/A100)
• Knowledge of Tenstorrent AI ASICs or other specialized AI hardware
   

What We Offer:

• Opportunity to work with cutting-edge AI infrastructure
• High performance-based bonuses tied to achieved weight improvements
• Potential for full-time position with percentage of mining profits
• Flexible remote work environment
• Access to high-end GPU hardware for experimentation
   

Application Process: Intrested candidates should submit their resume along with a brief description of their relevant experience in ML optimization or performance enhancement ideas.