CareerPlan

Principal Software Engineer - AI Inference and Serving (CoreAI)

United States, Washington, RedmondFull-time2026-11-17 → 2026-11-19

Core

Design and optimize high-performance AI inference systems, focusing on throughput, latency, and cost efficiency for model serving.

Role type

Principal Software Engineer (AI Inference and Serving)

Builds

Secure, tenant-isolated AI inference systems with automated testing and observability

Domain

Artificial Intelligence / Distributed Systems / Model Serving

Deliverable

production ML models

Required skills

C, C++, C#, Java, JavaScript, Python, distributed services, model serving, debugging, cross-team communication, containerization, Kubernetes, vLLM, SGLang, TensorRT-LLM

Preferred skills

prefix caching, prefill/decode disaggregation, speculative decoding, quantization, tensor/expert parallelism, capacity planning, incident prevention, mentorship

Technologies

Kubernetes, vLLM, SGLang, TensorRT-LLM

Responsibilities

Evaluate and implement optimization techniques for AI inference; lead capacity planning and incident prevention; mentor engineers; build secure, tenant-isolated systems; improve services using production feedback; pursue near-linear throughput scaling.

Seniority

Principal, hands-on IC with mentorship