LLM Engineer (Optimization)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 1 hour agoStatus: Live

Job Summary

Optimize large language model inference for real-world production: improve latency, throughput, and memory efficiency across long-context and multi-turn conversations. Build and accelerate GPU/accelerator-based inference engines and runtimes using modern frameworks (vLLM, TensorRT-LLM, SGLang, llama.cpp, ONNX Runtime, MLX). Advance model compression and compiler/kernel optimizations (quantization, CUDA/Triton/TVM/MLIR) and benchmark performance across hardware backends.

Location: South Korea

Workplace: Hybrid

Employment Type: Full time

Job Function: Software Engineering

Key Responsibilities

•Optimize LLM inference performance for latency, throughput, and memory efficiency.
•Research and apply optimization methods for different model architectures and inference environments.
•Develop and optimize GPU/accelerator-based inference engines and runtimes using inference frameworks.
•Apply model compression and compiler/kernel optimization (quantization, pruning, distillation; CUDA/Triton/TensorRT/TVM/MLIR) to improve inference performance.
•Analyze and benchmark performance across hardware and inference backends using profiling tools, tuning quality/cost/latency trade-offs and designing serving architecture.

Key Requirements

•3+ years of experience related to LLM, machine learning infrastructure, or inference optimization.
•Experience developing LLM inference engines or AI runtimes.
•Understanding of GPU architecture, CUDA programming, or parallel computing.
•Knowledge of model optimization techniques such as quantization, model compression, and compiler optimization.
•Experience with deep learning frameworks such as PyTorch, ONNX, and TensorRT.

Experience:3+ yearsLLMAI infrastructureInference optimization

Skills:Performance analysisProblem-solvingCollaboration

Tech Stack:VLLMTensorRT-LLMSGLangLlama.cppONNX RuntimeMLXCUDATritonTensorRTTVMMLIRSpeculative DecodingPrefill-Decode DisaggregationQuantizationPruningDistillationNVIDIA Nsight SystemsNVIDIA Nsight ComputePy-spyKubernetes

Company Brief

42dot

Website

Loading job details...

Preparing the role view and application actions.

42dot

3 weeks ago

LLM Engineer (Optimization)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 1 hour agoStatus: Live

Job Summary

Location: South Korea

Workplace: Hybrid

Employment Type: Full time

Job Function: Software Engineering

Key Responsibilities

•Optimize LLM inference performance for latency, throughput, and memory efficiency.
•Research and apply optimization methods for different model architectures and inference environments.
•Develop and optimize GPU/accelerator-based inference engines and runtimes using inference frameworks.
•Apply model compression and compiler/kernel optimization (quantization, pruning, distillation; CUDA/Triton/TensorRT/TVM/MLIR) to improve inference performance.
•Analyze and benchmark performance across hardware and inference backends using profiling tools, tuning quality/cost/latency trade-offs and designing serving architecture.

Key Requirements

•3+ years of experience related to LLM, machine learning infrastructure, or inference optimization.
•Experience developing LLM inference engines or AI runtimes.
•Understanding of GPU architecture, CUDA programming, or parallel computing.
•Knowledge of model optimization techniques such as quantization, model compression, and compiler optimization.
•Experience with deep learning frameworks such as PyTorch, ONNX, and TensorRT.

Experience:3+ yearsLLMAI infrastructureInference optimization

Skills:Performance analysisProblem-solvingCollaboration

Company Brief

42dot

Website