Production AI/ML Engineer — LLM Inference & RL Pipelines

Boundless Networks, Inc.; United States; Teletrabalho; USD 160 000 - 210 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Competitive salary + equity

Health, dental, vision

Flexible PTO

Conference budget

Remote-first

Resumo da oferta

Boundless Networks, Inc. is seeking an experienced AI-focused engineer to own end-to-end AI product delivery, from prototype to production, including model selection, serving, evaluation, and iteration.

You will deploy and optimize LLM inference across the fleet, tune batching, KV-cache, quantization, and multi-model routing for performance, cost, and reliability. Remote-first, global team with equity and growth opportunities.

Qualificações

• 3+ years shipping ML/AI systems to production.
• Hands-on experience serving LLM inference with vLLM, SGLang, or TensorRT-LLM.
• Experience with RL/post-training methods (GRPO, PPO, DPO, or SFT) or adjacent experience.
• Strong Python and PyTorch proficiency.
• Working understanding of GPU execution: batching, memory, CUDA basics.
• Comfort operating in ambiguity with a bias for action.

Responsabilidades

• Own end-to-end AI product delivery from prototype to production.
• Deploy and optimize LLM inference across the fleet.
• Build and operate RL/post-training pipelines.
• Develop eval harnesses and benchmarks to drive iteration.
• Collaborate with Infra on GPU scheduling and fleet utilization.

Conhecimentos

3+ years shipping ML/AI systems toprod

LLM inference experience (vLLM, SGLang

RL & post-training methods

Python

PyTorch

GPU understanding (batching/memory/CUD

Ferramentas

Kubernetes

Descrição da oferta de emprego

Boundless Networks, Inc. is seeking an experienced AI-focused engineer to own end-to-end AI product delivery, from prototype to production, including model selection, serving, evaluation, and iteration.

You will deploy and optimize LLM inference across the fleet, tune batching, KV-cache, quantization, and multi-model routing for performance, cost, and reliability. Remote-first, global team with equity and growth opportunities.