Ready to add some spice to your career? Solenya is fermenting the future with Zero-shot Discovery.

As our ML Engineer, you’ll be the secret ingredient in making our AI models go brrr…

Responsibilities

• Optimize model deployment, scaling, and runtime performance
• Implement MLOps best practices including experiment tracking, artifact versioning and end-to-end model validation
• Work with distributed training tools, CUDA-level optimization, and understand optimizations in inference-time featurization
• Apply techniques such as micro-batching, caching, and KV-caching for transformers

Qualifications

• 3+ years of work experience with postgraduate research in Machine Learning or related fields
• Comprehensive knowledge of modern deep learning architectures, parameter efficient fine-tuning, self-supervised pre-training and upcycling techniques
• Deep understanding of hardware, instruction sets and distributed systems architectures
• Experience with ONNX, TorchScript, quantization, and sparsification
• Proficiency in cloud infrastructure management using Terraform and Kubernetes

Send your github to careers@solenya.ai and tell us how you can spice up our team!