Inference & Workload Optimization Lead – Horizon AI

Job not on LinkedIn

πŸ•’ October 21

Where this job comes from

Posted on STN Incorporated's careers page β†—STN Incorporated's careers page, not through a job board

First seen by Remote Rocketship October 21

Still open on STN Incorporated's site. Checked 3 hours ago.

Apply Now
Logo of STN Incorporated

STN Incorporated

11 - 50 employees

Founded 2016

🏒 Enterprise

πŸ”’ Cybersecurity

πŸ”§ Hardware

Enterprise β€’ Cybersecurity β€’ Hardware

STN Incorporated is an enterprise-grade managed IT and cloud infrastructure provider that delivers secure, audit-ready infrastructure for business-critical systems and demanding AI workloads. STN operates a managed operating model offering private CPU clouds, GPU One AI infrastructure, secure networking and storage, and 24/7 human support with high uptime SLAs. Their services include managed infrastructure and cloud operations, cybersecurity operations and incident response, compliance and risk management (SOC 2 Type II, HIPAA-ready), backup and recovery, and enterprise technology procurement and lifecycle management. STN serves enterprises, high-growth SaaS companies, AI builders and model developers, robotics/physical AI firms, and regulated industries such as healthcare.

πŸ“‹ Description

β€’ Profile customer training and inference workloads to identify bottlenecks in data loading, collective communication, memory bandwidth, kernel efficiency, batching, and parallelism layout β€’ Establish performance baselines and define good performance for each hardware generation, starting with current-generation NVIDIA hardware β€’ Convert optimization expertise into agent-executable fixes applicable across customer clusters β€’ Work with committed-capacity customers, directly or through operating teams, on workload tuning β€’ Own internal model serving as a secondary responsibility, including cost- and latency-aware routing and model version migration β€’ Advise on GPU allocation between internal inference and customer workloads

🎯 Requirements

β€’ Deep GPU performance engineering, including profiling, memory and bandwidth behaviour, and kernel-level understanding β€’ Serving stack depth with technologies such as vLLM, SGLang, or TensorRT-LLM, including batching, KV cache management, and quantization trade-offs β€’ Distributed training and inference experience at scale, including tensor, pipeline, and data parallelism β€’ Experience tuning collective communication such as NCCL β€’ Fluency with profiling tools such as Nsight, DCGM, and framework-level profilers β€’ Ability to explain performance findings to customers and encode them for an agent β€’ Nice to have: CUDA kernel work, open-weight model deployment at scale, benchmark design, and prior customer-facing technical experience

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ October 21

Cencora

10,000+ employees

πŸ’Ό Consulting

πŸ“¦ Logistics

πŸ₯ Healthcare

AI initiatives director driving artificial intelligence strategy for Cencora’s healthcare services business. Identifying opportunities, governing execution, and improving financial and operational outcomes.

πŸ•’ October 21

Pencil

51 - 200

πŸ€– Artificial Intelligence

πŸ“£ Marketing

🀝 B2B

AI Transformation Lead driving enterprise adoption of Pencil’s Generative AI advertising SaaS. Leading client transformation engagements, AI process design, stakeholder change, and product feedback.

πŸ•’ October 21

RevStar

51 - 200

πŸ’Ό Consulting

🀝 B2B

πŸ€– Artificial Intelligence

Forward Deployed Engineer delivering AWS cloud, data, and Generative AI solutions for enterprise clients at RevStar. Leading migrations, modernization, enterprise GenAI architectures, and technical growth initiatives.

πŸ•’ October 21

RevStar

51 - 200

πŸ’Ό Consulting

🀝 B2B

πŸ€– Artificial Intelligence

Forward Deployed Engineer delivering AWS cloud, data, and Generative AI solutions for enterprise clients. Leading migrations, modernization, GenAI deployments, and executive-facing technical delivery.

πŸ•’ October 21

Datavail

1001 - 5000

πŸ’Ό Consulting

πŸ₯ Healthcare

πŸ“¦ Logistics

Senior AI and data governance advisor designing responsible governance frameworks for enterprise clients. Translating AI regulations into practical controls and leading engagements, offerings, and team development.

Built byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok