AI Research Engineer – Kernel & Inference Optimization

This is a fully remote position, open to applicants in Italy.

📋 Description

• Foster innovation in model serving and inference architectures

• Enhance model deployment and inference methodologies

• Develop resource-efficient models suitable for constrained hardware

• Create resilient inference pipelines

• Set up comprehensive performance evaluation metrics

• Detect and address bottlenecks within production environments

⛳️ Requirements

• A degree in Computer Science or a related discipline

• Preferably a PhD in NLP, Machine Learning, or a similar area

• Familiarity with Metal Shading Language (MSL)

• Demonstrated experience in low-level kernel optimizations

• Strong proficiency in writing GPU kernels for mobile platforms

• Hands-on experience in creating and deploying end-to-end inference pipelines

• In-depth knowledge of contemporary model serving architectures

• Experience with Distributed Inference Systems and techniques such as Tensor Parallelism

• Comprehension of advanced optimization techniques

🏝️ Benefits

• Work remotely from any location globally

• Opportunity for collaboration with international teams

• Engage in cutting-edge projects within the fintech sector