Inference Infrastructure Engineer, Serving

Elorian•Palo Alto, CA

1d•$275,000 - $475,000•Onsite

About The Position

We are a well-funded, early-stage AI lab focused on building the next generation of frontier multimodal AI models. Founded by former DeepMind researchers, including Andrew Dai, who was previously a leader on Gemini. Our team currently consists of 20 world-class scientists and engineers. We recently raised $55M in seed funding from Striker Ventures, Menlo Ventures, Altimeter Capital, and NVIDIA. We are tackling some of the hardest problems in artificial intelligence, and we are growing fast. We're looking for an infrastructure engineer to design, optimize, and scale the systems that serve our large multimodal models. Your work will make inference faster, more cost-effective, and more reliable, so our teams can focus on advancing model capabilities rather than managing bottlenecks. Our focus is on performant, efficient inference, both to power real-world applications and to accelerate research. This role owns the infrastructure that ensures every deployment and evaluation runs smoothly at scale for our visual foundation models.

Requirements

3+ years of experience building low-latency, high-throughput inference serving systems for large models
Strong knowledge of inference optimization techniques (quantization, batching, speculative decoding, KV cache management)
Hands-on experience with serving frameworks such as vLLM, TensorRT-LLM, Triton, or SGLang
Experience with multi-GPU/multi-node model parallelism for serving (tensor or pipeline parallel)
Strong systems programming skills; C++/CUDA a plus alongside Python
Experience with autoscaling and load balancing for production ML services
A track record of GPU cost optimization at scale

Nice To Haves

Experience serving multimodal (vision + language) models
Contributions to open-source ML or systems infrastructure projects (e.g., vLLM, SGLang, TensorRT-LLM, Triton)
A bias for action and comfort working across stacks and teams in an early-stage environment

Responsibilities

Build low-latency, high-throughput inference serving systems for our large multimodal models
Design and implement techniques that improve latency, throughput, and efficiency, including quantization, batching, speculative decoding, and KV cache management
Optimize our codebase and GPU fleet to fully utilize hardware FLOPs, bandwidth, and memory
Implement multi-GPU and multi-node model parallelism for serving (tensor or pipeline parallel)
Build autoscaling and load balancing for production ML services
Establish standards for reliability, observability, and reproducibility across the inference stack
Collaborate with researchers to enable high-performance inference for novel architectures