SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Hippocratic AI is seeking an LLM Inference Systems Engineer to design and operate the distributed serving and high-performance networking layer for large language models. This role owns the full stack from model server to GPU fabric, including prefill/decode disaggregation, KV-cache transfer, multi-node execution, and production observability.
You will design and implement disaggregated LLM serving architectures with independent prefill and decode pools, KV-cache transfer, routing, batching, and failure recovery. You'll optimize multi-node inference across modern GPU systems using NVLink, NVSwitch, NVLS, InfiniBand, RoCEv2, GPUDirect RDMA, NCCL, UCX, and related communication paths. You'll build and tune serving systems using frameworks like SGLang, vLLM, NVIDIA Dynamo, or TensorRT-LLM.
Key responsibilities include profiling end-to-end performance across compute, memory, network, and storage to improve time to first token, inter-token latency, throughput, tail latency, and cost per token. You'll develop repeatable benchmark and capacity-planning workflows across model architectures, GPU types, and parallelism strategies. You'll productionize serving on Kubernetes with health checks, autoscaling, safe rollouts, metrics, tracing, and diagnostics. You'll diagnose complex distributed failures such as collective timeouts, topology mismatches, packet loss, congestion, KV-transfer stalls, GPU OOMs, and uneven load. You'll partner closely with model researchers and platform engineers to launch new models, serving features, and hardware generations safely.
The role sits within the Inference team in the Model organization and partners closely with Model, Infrastructure, and Application engineering teams. This is a five-days-per-week in-office role in Menlo Park.
Hippocratic AI is building the world's first healthcare-only, safety-focused LLM platform. The company was co-founded by CEO Munjal Shah and a team of physicians, hospital leaders, and AI pioneers from institutions including El Camino Health, Johns Hopkins, Stanford, Google, Meta, Microsoft, and NVIDIA. The company recently raised a $126M Series C at a $3.5B valuation, bringing total funding to $404M with participation from CapitalG, General Catalyst, a16z, Kleiner Perkins, and leading healthcare investors.
REQUIREMENTS:
Must-have:
- Production experience building or operating distributed systems, high-performance computing systems, or large-scale ML inference platforms
- Strong understanding of LLM inference, including tensor/pipeline/data parallelism, continuous batching, KV-cache management, and prefill/decode behavior
- Hands-on experience with GPU communication and networking technologies such as NCCL, NVLink/NVSwitch, InfiniBand, RoCE, RDMA, UCX, or equivalent systems
- Strong Python skills and working proficiency in C++ or another systems language
- Ability to profile and debug performance across application, runtime, kernel, network, and infrastructure layers
- Experience deploying production workloads on Kubernetes and operating them with clear reliability and observability standards
- Clear written and verbal communication across research, infrastructure, and product-facing teams
- Master's degree or PhD required
Nice-to-have:
- Direct experience with disaggregated serving, KV-cache transfer, NVIDIA Dynamo/NIXL, SGLang, vLLM, or TensorRT-LLM
- Experience with NVLS, SHARP, GPUDirect RDMA, UCX, RDMA congestion control, or GPU-cluster topology optimization
- CUDA, Triton, custom kernel, or low-level GPU performance experience
- Experience with speculative decoding, multi-LoRA serving, quantization, or cache-aware routing
- Contributions to open-source inference, networking, or distributed-systems projects
- Experience benchmarking new GPU platforms and turning results into production architecture decisions
