Resumo da vaga

Machine Learning Engineer — Inference Optimization

Requisitos e responsabilidades

Conteúdo da vaga extraído em seções para revisão mais rápida.

What You’ll Do

  • Optimize inference latency, throughput, and cost for large-scale ML models in production
  • Profile and bottleneck GPU/CPU inference pipelines (memory, kernels, batching, IO)
  • Implement and tune techniques such as:Quantization (fp16, bf16, int8, fp8)KV-cache optimization & reuseSpeculative decoding, batching, and streamingModel pruning or architectural simplifications for inference
  • Quantization (fp16, bf16, int8, fp8)
  • KV-cache optimization & reuse
  • Speculative decoding, batching, and streaming
  • Model pruning or architectural simplifications for inference
  • Collaborate with research engineers to productionize new model architectures
  • Build and maintain inference-serving systems (e.g. Triton, custom runtimes, or bespoke stacks)
  • Benchmark performance across hardware (NVIDIA / AMD GPUs, CPUs) and cloud setups
  • Improve system reliability, observability, and cost efficiency under real workloads

Implement and tune techniques such as:

  • Quantization (fp16, bf16, int8, fp8)
  • KV-cache optimization & reuse
  • Speculative decoding, batching, and streaming
  • Model pruning or architectural simplifications for inference

What We’re Looking For

  • Strong experience in ML inference optimization or high-performance ML systems
  • Solid understanding of deep learning internals (attention, memory layout, compute graphs)
  • Hands-on experience with PyTorch (or similar) and model deployment
  • Familiarity with GPU performance tuning (CUDA, ROCm, Triton, or kernel-level optimizations)
  • Experience scaling inference for real users (not just research benchmarks)
  • Comfortable working in fast-moving startup environments with ownership and ambiguity

Nice to haves

  • Experience with LLM or long-context model inference
  • Knowledge of inference frameworks (TensorRT, ONNX Runtime, vLLM, Triton)
  • Experience optimizing across different hardware vendors
  • Open-source contributions in ML systems or inference tooling
  • Background in distributed systems or low-latency services

Why Join Us

  • Real ownership over performance-critical systems
  • Direct impact on product reliability and unit economics
  • Close collaboration with research, infra, and product
  • Competitive compensation + meaningful equity at Series A
  • A team that cares about engineering quality, not hype
Vagas similares

Mantenha uma lista reserva.

Ver stack
FocoAI Optimization EngineerÁrea da vaga
Sinal de senioridadeMiddleNível do candidato
StackLLMSkills principais
Localização5 países aceitosElegibilidade

Stack

Use estas tags para comparar vagas remotas similares.

Elegibilidade de localização

Candidatos devem aplicar apenas quando o país do perfil estiver listado aqui.

Seu perfilPaís não definidoEntre para comparar seu país com esta vaga.

Fluxo de contratação

O WithMira mostra a vaga e depois envia candidatos para a aplicação da empresa.

1Confira fit da vaga, stack e elegibilidade de localização no WithMira.
2Abra a página de aplicação da empresa pelo link rastreado.
3Salve a vaga ou assine oportunidades similares antes de sair.