Principal Software Engineer | Microsoft Careers

Microsoft

Actively hiring Verified listing

WA Posted 62 days ago $142,800–$274,800 / year

View original post Log in to save

At a glance

AI generated

TL;DR

As a Principal Software Engineer on the Ads Engineering Platform team at Microsoft Advertising, you will lead the development of high-performance ad-serving infrastructure that powers Bing Search, MSN, Microsoft Start, and Edge browser shopping experiences. Your role involves designing and optimizing large-scale distributed systems with GPU-accelerated inference frameworks to process millions of ad requests per second efficiently. You’ll work on end-to-end inference infrastructure, including model serving, caching, scheduling, and resource orchestration across heterogeneous hardware. Key responsibilities include profiling and optimizing performance at the CUDA kernel level, ensuring live-site reliability through telemetry and fault-tolerance mechanisms, and collaborating with cross-functional teams to drive architectural excellence. Preferred qualifications include experience in real-time data streaming systems, LLM inference optimization, GPU inference frameworks like NVIDIA Triton Inference Server, and deep expertise in system-level optimizations for transformer/LLM architectures.

Skills

CUDA NVIDIA_Triton_Inference_Server TensorRT Kafka Flink Spark_Streaming GPU CPU NUMA Docker CI/CD Prometheus Grafana PostgreSQL Python Go AWS Azure Google_Cloud_Pods Kubernetes Terraform

What you'll do

Design and lead development of high-performance ad-serving systems with ultra-low latency.
Optimize end-to-end inference infrastructure for cost efficiency across heterogeneous hardware.
Profile and optimize full-stack performance, identifying and resolving bottlenecks in real-time.
Own live-site reliability by designing telemetry and fault-tolerance mechanisms globally.
Mentor team members on deep debugging, profiling, and system-level optimization practices.

What we're looking for

Extensive experience in designing and optimizing high-performance ad-serving systems.
Hands-on expertise with real-time data streaming systems and multi-region deployment.
Deep knowledge of LLM inference optimization techniques including model sharding and quantization.
Proven success in operating large-scale systems with SLA-based capacity forecasting and autoscaling.
Expertise in GPU inference frameworks like NVIDIA Triton Inference Server, CUDA, and TensorRT.
Solid understanding of model-serving trade-offs and optimization strategies for deep learning workloads.

Market check

Salary context

This $142,800–$274,800 range sits above 67% of similar postings on FindRole.

Peer median band

$142,050–$264,000

Median floor and ceiling across peers.

Typical midpoint (25–75%)

$177,250–$214,500

Middle half of comparable postings.

Based on 240 comparable postings.

* 240 is the maximum number of comparable postings sampled.

Employer

About Microsoft

Microsoft Corporation is a global technology leader producing software, hardware, and cloud services including Windows, Office 365, Azure cloud platform, Xbox gaming, and Surface devices. Industry: Software & Cloud Computing

Microsoft currently has 534 open roles on FindRole.

Microsoft

US 9 days ago $165,600–$296,400

Azure Kubernetes Docker CI/CD Apache Spark Kafka PostgreSQL Redis GraphQL Python JavaScript TypeScript React Node.js ML/AI Data pipelines Microservices APIs Schema evolution Telemetry Operational excellence

Hybrid