Senior Inference Engineer, AGI

What you'll do

• Co-design model architectures and optimize inference paths, kernels, and GPU performance for latency, memory, and cost.
• Build and operate real-time streaming serving systems, including scheduling, batching, multi-GPU inference, and performance benchmarking.
• Build offline rollout, reward-serving, training, and evaluation infrastructure, maintaining consistency with production inference.

What they ask for

• 5+ years of non-internship professional software development experience and 5+ years programming in at least one language.
• 4+ years leading design or architecture of new and existing systems.
• Bachelor's degree in computer science or equivalent; experience as a mentor, tech lead, or engineering team lead.
• 2+ years hands-on neural-model inference optimization, plus deep-learning, GPU optimization, and production experience with latency-constrained real-time inference under concurrent load.

Nice to have

• Production LLM or multimodal serving internals, custom GPU kernels, or real-time streaming AI systems.
• Offline reinforcement-learning inference infrastructure, distributed training, multiple hardware backends, or speech/audio generative models.

Pay

193,300.00 - 261,500.00 USD annually (base salary); 168,100.00 - 227,400.00 USD annually (base salary); 168,100.00 - 227,400.00 USD annually (base salary)

Tools

vLLM, PyTorch, Nsight Compute/Systems, INT8/FP8/BF16, CUTLASS, Triton, CUDA/PTX, NCCL

AI focus

Inference engineering for real-time multimodal conversational AI, including speech/audio models, model efficiency, streaming serving, reinforcement learning, and evaluation.