DontApply.Club
Login Register

Software Engineer, Distributed AI Infrastructure

Jobverse Io — United States · Posted ~3 hours ago

Full-time

Skills

distributed systems backend engineering model serving AI inference data processing scalable systems data pipelines performance optimization monitoring high availability backend infrastructure

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

Build the distributed backend infrastructure that powers advanced AI capabilities. You will develop high-throughput systems for model serving and inference, create resilient data processing pipelines, optimize resource utilization and latency, and ensure data integrity, tenant isolation, monitoring, and high availability.

Highlights

Work on large-scale AI infrastructure involving distributed systems, model inference, resilient backend services, massive data pipelines, performance optimization, and highly available platforms.

Description

Docusign provides intelligent agreement management solutions that help organizations create, manage, and process agreements. The Software Engineer will build distributed systems and backend infrastructure for AI capabilities, including model serving, inference, data processing, and scalable platforms for advanced AI applications. Responsibilities Build and maintain high-performance distributed systems to support large-scale model inference and data processingDesign and build resilient, horizontally scalable backend services capable of handling high-throughput data processing and model interactionDevelop the core infrastructure for model serving and inference runtimes, focusing on maximizing resource utilization and minimizing latencyArchitect resilient data ingestion and processing pipelines that handle massive datasets while ensuring data integrity, multi-tenant isolation, and high availabilityOptimize system performance, identify bottlenecks, and implement advanced monitoring (SLOs, SLAs) to ensure high reliability for mission-critical AI services