Machine Learning Systems Engineer
Amit SuryawanshiUnited StatesSENIORPosted 5d ago
Machine LearningLLM Inference OptimizationAWS Trainium2AWS Trainium3AWS Neuron SDKPythonPyTorchvLLMTensorRT-LLMSGLangTriton Inference ServerSpeculative DecodingMulti-Token PredictionPerformance BenchmarkingAccelerator OptimizationCUDATritonNKI Kernel Development
About the Role
We are looking for an experienced Machine Learning Systems Engineer with strong expertise in LLM inference optimization and AWS Trainium platforms.
Key Responsibilities
• Optimize production-grade LLM inference
• Reduce decode latency
• Improve throughput and cost performance
Requirements
• Strong expertise in Machine Learning Systems & LLM Inference Optimization
• Experience with AWS Trainium2 / Trainium3, AWS Neuron SDK
• Proficiency in Python & PyTorch
• Familiarity with vLLM, TensorRT-LLM, SGLang, or Triton Inference Server
• Knowledge of Speculative Decoding & Multi-Token Prediction
• Experience with Performance Benchmarking & Accelerator Optimization
• Skills in CUDA, Triton, or NKI Kernel Development