AI Researcher — Inference Optimization

Featherlessai; United States; Remoto; USD 140.000 - 210.000; Tempo pieno

Descrizione del lavoro

Featherlessai in the United States is seeking a specialist to optimize inference for large neural networks, focusing on latency, throughput, memory efficiency, and cost per inference.

You will design model-level optimizations like quantization and pruning, plus systems-level work such as dynamic batching, multi-GPU inference, and deployment of optimized pipelines.

Collaborate with teams to translate research into production improvements and benchmark across accelerators.

Competenze

• Strong background in machine learning, deep learning, or AI systems.
• Hands-on experience optimizing inference for large-scale models.
• Proficiency in Python and modern ML frameworks like PyTorch.
• Experience with inference tooling such as Triton, TensorRT, vLLM, or ONNX Runtime.
• Ability to design experiments and communicate results clearly.

Mansioni

• Research and develop techniques to optimize inference performance for large neural networks
• Improve latency, throughput, memory efficiency, and cost per inference
• Design and evaluate model-level optimizations such as quantization, pruning, and KV-cache optimization
• Implement systems-level optimizations including dynamic batching, kernel fusion, and multi-GPU inference
• Benchmark inference workloads across hardware accelerators
• Collaborate with engineering teams to deploy optimized inference pipelines
• Translate research insights into production-ready improvements

Conoscenze

ML / AI systems

Python

PyTorch

Experiment design

Communication of results

Strumenti

Triton

TensorRT

vLLM

ONNX Runtime

Descrizione del lavoro

Responsibilities

• Research and develop techniques to optimize inference performance for large neural networks
• Improve latency, throughput, memory efficiency, and cost per inference
• Design and evaluate model-level optimizations such as quantization, pruning, and KV-cache optimization
• Implement systems-level optimizations including dynamic batching, kernel fusion, and multi-GPU inference
• Benchmark inference workloads across hardware accelerators
• Collaborate with engineering teams to deploy optimized inference pipelines
• Translate research insights into production-ready improvements

Requirements

• Strong background in machine learning, deep learning, or AI systems
• Hands-on experience optimizing inference for large-scale models
• Proficiency in Python and modern ML frameworks like PyTorch
• Experience with inference tooling such as Triton, TensorRT, vLLM, or ONNX Runtime
• Ability to design experiments and communicate results clearly

Preferred Qualifications

• Experience deploying production inference systems at scale
• Familiarity with distributed and multi-GPU inference
• Experience contributing to open-source ML or inference frameworks
• Authorship or co-authorship of peer-reviewed research papers
• Experience working close to hardware using CUDA, ROCm, or profiling tools