Applied AI/ML Engineer — Build AI at Scale (Remote)

Boundless Networks; United States; Remote; USD 175,000 - 250,000; Full time

Benefits offered by this job

Equity allocation

Health, dental, vision

Flexible PTO

Conference travel budget

Remote-first with off-sites

Professional development

Job summary

Boundless is hiring an Applied AI/ML Engineer to ship AI-powered products end-to-end on our growing GPU inference fleet. You’ll own everything from serving low-latency inference to post-training pipelines, with a bias for action and autonomy.

You’ll deploy LLM inference, optimize throughput and cost, and build evaluation harnesses to drive fast iteration. A strong foundation in Python and PyTorch, plus GPU concepts, is required.

Qualifications

• 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).
• Strong Python and PyTorch.
• Working understanding of GPU execution: batching, memory, and CUDA concepts.
• Comfort operating in ambiguity with a strong bias for action.

Responsibilities

• Own AI features and products from prototype through production — model selection, serving, evaluation, and iteration — shipping working software rather than research artifacts.
• Deploy and optimize LLM inference across the fleet using vLLM and SGLang. Tune batching, KV-cache management, quantization, speculative decoding, and multi-model routing to maximize throughput and minimize latency and cost per token.
• Build and operate RL and post-training pipelines using slime (Megatron-LM + SGLang) and Prime Intellect; design rewards and verifiers, orchestrate rollouts, synchronize weights, and ensure long-running training stability.
• Build eval harnesses and benchmarks measuring quality, throughput, and cost to drive fast iteration.
• Partner with Infrastructure on GPU scheduling and fleet utilization, and with Product on what to build next and why.

Skills

ML systems

LLM inference

Python

PyTorch

RL methods

CUDA basics

Ambiguity tolerance

Tools

vLLM

SGLang

TensorRT-LLM

Megatron-LM

Job description

Boundless is hiring an Applied AI/ML Engineer to ship AI-powered products end-to-end on our growing GPU inference fleet. You’ll own everything from serving low-latency inference to post-training pipelines, with a bias for action and autonomy.

You’ll deploy LLM inference, optimize throughput and cost, and build evaluation harnesses to drive fast iteration. A strong foundation in Python and PyTorch, plus GPU concepts, is required.