AI Research Engineer, Kernel & Inference Optimization

• Design and deploy state-of-the-art model serving architectures with high throughput, low latency, and optimized memory usage
• Ensure inference pipelines run efficiently across resource-constrained devices and edge platforms
• Establish performance targets for latency, token response, and memory footprint
• Build, run, and monitor controlled inference tests in simulated and live production environments
• Track latency, throughput, memory consumption, and error-rate KPIs
• Document iterative results and compare outcomes against established benchmarks across platforms
• Identify and prepare test datasets and simulation scenarios for low-resource deployment challenges
• Analyze computational efficiency and diagnose serving-pipeline bottlenecks
• Optimize batch processing, network delays, memory usage, scalability, and reliability
• Collaborate with cross-functional teams to integrate optimized serving and inference frameworks into production edge and on-device pipelines
• Define success metrics and perform continuous monitoring and iterative refinements

• A degree in Computer Science or related field
• Ideally PhD in NLP, Machine Learning, or a related field
• Solid track record in AI R&D, with good publications in A* conferences
• Knowledge of Metal Shading Language (MSL)
• Ability to write custom compute shaders from scratch
• Proven experience in low-level kernel optimizations and inference optimization on mobile devices
• Measurable improvements in inference latency, throughput, and memory footprint for domain-specific applications
• Deep understanding of modern model serving architectures and inference optimization techniques
• Strong expertise in writing GPU kernels for mobile devices such as smartphones
• Deep understanding of model serving frameworks and engines
• Practical experience developing and deploying end-to-end inference pipelines on resource-constrained devices
• Ability to apply empirical research to model-serving challenges including latency optimization, computational bottlenecks, and memory constraints
• Proficiency in designing evaluation frameworks and iterating on optimization strategies
• Experience with distributed inference systems, including Tensor Parallelism, Pipeline Parallelism, and Expert Parallelism
• Deep understanding of the mathematics and structure of Diffusion Models and Vision Transformers
• Understanding of Pruning, Quantization, Flash Attention, KV Cache, and Speculative Decoding (Eagle)

• Remote work from anywhere in the world
• Opportunity to collaborate with a global team
• Work on innovative fintech, blockchain, AI, and digital finance products