AI Researcher (Inference Optimization)

TL;DR

AI Researcher (Inference Optimization): Design, evaluate, and deploy high-performance inference systems for large-scale machine learning models with an accent on model architecture, systems engineering, and hardware-aware optimization. Focus on researching and implementing model-level and systems-level optimizations to improve latency, throughput, memory efficiency, and cost per inference.

Location: Remote (world)

Company

hirify.global develops optimized inference systems for production AI environments.

What you will do

• 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 like quantization, pruning, KV-cache optimization, and architecture simplifications.
• Implement systems-level optimizations including dynamic batching, kernel fusion, multi-GPU inference, and prefill vs decode strategies.
• Benchmark inference workloads across hardware accelerators and collaborate on deploying optimized 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 (e.g., PyTorch).
• Experience with inference tooling (e.g., Triton, TensorRT, vLLM, ONNX Runtime).
• Ability to design experiments and communicate results clearly.

Nice to have

• 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 in machine learning or systems.
• Experience working close to hardware (CUDA, ROCm, profiling tools).

Culture & Benefits

• Work in a collaborative environment focused on measurable impact in production systems.
• Opportunity to translate research into real-world deployments.
• Emphasis on clear benchmarks, documentation, and informing product decisions.