Principal Machine Learning Engineer

What you'll do

• Architect technical infrastructure for serving heterogeneous generative model pipelines including LLMs, diffusion models, and 3D systems.
• Optimize inference performance across GPU fleets to improve latency, throughput, and cost-efficiency.
• Develop and optimize GPU-accelerated inference code using tools like PyTorch, CUDA, Triton, and TensorRT.
• Design the product backend and API layers for internal applications and external plugin integrations.
• Provide hands-on technical leadership and mentorship to a growing team of machine learning engineers.
• Research and evaluate emerging MLOps technologies such as quantization and GPU scheduling to improve system performance.
• Establish technical standards and lead design reviews to ensure high reliability across all generative AI services.

What we're looking for

• MS or PhD in Computer Science, Machine Learning, or a related field (or equivalent experience).
• 8+ years of experience in machine learning engineering with production-scale deployment and serving.
• 3+ years leading the technical direction of large-scale, GPU-intensive GenAI inference systems.
• Deep experience with PyTorch, CUDA, Triton, TensorRT, Nvidia Dynamo, and Python.
• Strong understanding of generative model architectures including diffusion models, transformers, GANs, and LLMs.
• Proven experience architecting multi-model pipelines and product backend systems at enterprise scale.
• Experience with model serving, orchestration, and GPU resource management in large-scale environments (preferred).
• Hands-on expertise in Kubernetes, distributed systems, MLOps platforms, RAG architectures, and quantization techniques (preferred).