Skip to main content
Loading
loadingbar
Loading, Please wait..!!

Senior Solutions Architect — AI Inference & Model Serving

  • Senior Solutions Architect — AI Inference & Model Serving job type Posted on: Nov 17, 2026
  • Senior Solutions Architect — AI Inference & Model Serving experience level Saturn Cloud
  • Senior Solutions Architect — AI Inference & Model Serving employment type pittsburgh, Pennsylvania
  • Senior Solutions Architect — AI Inference & Model Serving salary Salary: $170,000 per year
  • Senior Solutions Architect — AI Inference & Model Serving employment type Onsite
  • Senior Solutions Architect — AI Inference & Model Serving salary Full-time

Point Apply Here APPLY LATER

Curious about compensation?

Explore the historical salary trends, average pay, and estimated compensation for Senior Solutions Architect — AI Inference & Model Serving roles in Pennsylvania.

View Salary Guide →

Job Title :

Senior Solutions Architect — AI Inference & Model Serving

Job Type :

Full-Time

Job Location :

pittsburgh Pennsylvania United States

Remote :

No

Jobcon Logo Job Description :

Remote — United States | Full-TimeAbout Saturn CloudSaturn Cloud builds infrastructure software for deploying and operating production AI workloads.Our Token Factory platform helps GPU cloud operators and enterprises run AI inference services on their own infrastructure. It supports open-weight model serving, fine-tuning, OpenAI-compatible APIs, multi-tenant management, usage metering, and billing.We work at the intersection of GPU infrastructure, machine learning, and the operational systems needed to deliver AI services at scale.About the RoleWe're hiring a Senior Solutions Architect to help enterprise customers and infrastructure partners evaluate, deploy, and operate Saturn Cloud's AI infrastructure platform.You'll work directly with customers to understand their technical requirements, design solutions, lead evaluations, and help move AI workloads into production.This is a highly technical, customer-facing role that combines cloud architecture, machine learning infrastructure, and hands-on problem-solving. You'll collaborate closely with sales and engineering while serving as a trusted technical advisor to our customers.What You'll DoLead technical discovery with enterprise customers and AI infrastructure partners to understand workloads, architecture, constraints, and deployment requirements.Design solutions using Saturn Cloud's Token Factory, model serving, fine-tuning, and infrastructure management capabilities.Help customers evaluate and deploy open-weight models through dedicated inference endpoints and OpenAI-compatible APIs.Design and execute technical proofs of concept, product demonstrations, and customer evaluations.Work with customers to assess GPU requirements, inference throughput, latency, scaling, reliability, and deployment economics.Advise on multi-tenant architectures, API access, usage metering, security, and production operations.Collaborate with enterprise sales and engineering to develop technical proposals, deployment plans, and customer-specific architectures.Troubleshoot deployment and integration challenges, escalating product or infrastructure issues to engineering as needed.Develop reusable demonstrations, reference architectures, documentation, and technical guidance.Bring customer feedback to engineering to help improve the product.What We're Looking ForApproximately 5+ years of experience in solutions architecture, sales engineering, infrastructure engineering, ML engineering, or a similar technical role.Strong practical understanding of cloud infrastructure, including AWS, Google Cloud, Azure, or GPU cloud providers.Experience with containers, Kubernetes, networking, and production application deployment.Proficiency with Python and experience working with APIs and developer tools.Familiarity with machine learning infrastructure, model deployment, or inference serving.Ability to understand and explain system architecture, technical tradeoffs, and performance considerations.Experience working directly with technical customers, including discovery, demonstrations, troubleshooting, or proofs of concept.Strong written and verbal communication skills, including the ability to communicate with both engineers and business stakeholders.Comfort working independently and collaborating closely with engineering teams.Especially Interesting ExperienceHands-on experience deploying large language models or other open-weight models in production.Familiarity with inference serving frameworks such as vLLM, SGLang, NVIDIA Triton, or TensorRT-LLM.Knowledge of GPU architectures, memory constraints, batching, quantization, and inference performance optimization.Experience with fine-tuning techniques such as LoRA and other parameter-efficient approaches.Experience designing multi-tenant platforms, authentication and authorization systems, usage metering, or consumption-based billing.Experience deploying infrastructure into customers' own cloud environments, private infrastructure, or on-premises systems.Previous work at an AI infrastructure company, inference service provider, GPU cloud platform, or enterprise ML platform.Why Saturn CloudYou'll work on real infrastructure problems with direct exposure to customers and the people building the product.You'll help organizations operate AI workloads in production, balancing performance, reliability, cost, and practical deployment constraints.As part of a startup, you'll have substantial technical ownership and the opportunity to influence product development through direct customer experience.Saturn Cloud operates as a distributed, remote-first team.Compensation & BenefitsAnnual base salary: $170,000–$205,000Equity participationCompany-paid medical, dental, and vision coverage for employees and eligible family membersFlexible paid time off, with a 15-day annual minimumRemote-first work environmentApplyInterested in helping organizations deploy and operate production AI infrastructure?Submit your resume and a brief introduction describing your experience with cloud architecture, AI infrastructure, or production model serving.Saturn Cloud is an equal opportunity employer. We evaluate candidates based on their qualifications and ability to contribute to the role.

Jobcon Logo Position Details

Posted:

Nov 17, 2026

Reference Number:

29263_2712508002979545088374240

Employment:

Full-time

Salary:

$170,000 per year

City:

pittsburgh

Job Origin:

APPCAST_CPC

Share this job:

  • linkedin

Jobcon Logo
A job sourcing event
In Dallas Fort Worth
Aug 19, 2017 9am-6pm
All job seekers welcome!

Senior Solutions Architect — AI Inference & Model Serving    Apply

Click on the below icons to share this job to Linkedin, Twitter!

Remote — United States | Full-TimeAbout Saturn CloudSaturn Cloud builds infrastructure software for deploying and operating production AI workloads.Our Token Factory platform helps GPU cloud operators and enterprises run AI inference services on their own infrastructure. It supports open-weight model serving, fine-tuning, OpenAI-compatible APIs, multi-tenant management, usage metering, and billing.We work at the intersection of GPU infrastructure, machine learning, and the operational systems needed to deliver AI services at scale.About the RoleWe're hiring a Senior Solutions Architect to help enterprise customers and infrastructure partners evaluate, deploy, and operate Saturn Cloud's AI infrastructure platform.You'll work directly with customers to understand their technical requirements, design solutions, lead evaluations, and help move AI workloads into production.This is a highly technical, customer-facing role that combines cloud architecture, machine learning infrastructure, and hands-on problem-solving. You'll collaborate closely with sales and engineering while serving as a trusted technical advisor to our customers.What You'll DoLead technical discovery with enterprise customers and AI infrastructure partners to understand workloads, architecture, constraints, and deployment requirements.Design solutions using Saturn Cloud's Token Factory, model serving, fine-tuning, and infrastructure management capabilities.Help customers evaluate and deploy open-weight models through dedicated inference endpoints and OpenAI-compatible APIs.Design and execute technical proofs of concept, product demonstrations, and customer evaluations.Work with customers to assess GPU requirements, inference throughput, latency, scaling, reliability, and deployment economics.Advise on multi-tenant architectures, API access, usage metering, security, and production operations.Collaborate with enterprise sales and engineering to develop technical proposals, deployment plans, and customer-specific architectures.Troubleshoot deployment and integration challenges, escalating product or infrastructure issues to engineering as needed.Develop reusable demonstrations, reference architectures, documentation, and technical guidance.Bring customer feedback to engineering to help improve the product.What We're Looking ForApproximately 5+ years of experience in solutions architecture, sales engineering, infrastructure engineering, ML engineering, or a similar technical role.Strong practical understanding of cloud infrastructure, including AWS, Google Cloud, Azure, or GPU cloud providers.Experience with containers, Kubernetes, networking, and production application deployment.Proficiency with Python and experience working with APIs and developer tools.Familiarity with machine learning infrastructure, model deployment, or inference serving.Ability to understand and explain system architecture, technical tradeoffs, and performance considerations.Experience working directly with technical customers, including discovery, demonstrations, troubleshooting, or proofs of concept.Strong written and verbal communication skills, including the ability to communicate with both engineers and business stakeholders.Comfort working independently and collaborating closely with engineering teams.Especially Interesting ExperienceHands-on experience deploying large language models or other open-weight models in production.Familiarity with inference serving frameworks such as vLLM, SGLang, NVIDIA Triton, or TensorRT-LLM.Knowledge of GPU architectures, memory constraints, batching, quantization, and inference performance optimization.Experience with fine-tuning techniques such as LoRA and other parameter-efficient approaches.Experience designing multi-tenant platforms, authentication and authorization systems, usage metering, or consumption-based billing.Experience deploying infrastructure into customers' own cloud environments, private infrastructure, or on-premises systems.Previous work at an AI infrastructure company, inference service provider, GPU cloud platform, or enterprise ML platform.Why Saturn CloudYou'll work on real infrastructure problems with direct exposure to customers and the people building the product.You'll help organizations operate AI workloads in production, balancing performance, reliability, cost, and practical deployment constraints.As part of a startup, you'll have substantial technical ownership and the opportunity to influence product development through direct customer experience.Saturn Cloud operates as a distributed, remote-first team.Compensation & BenefitsAnnual base salary: $170,000–$205,000Equity participationCompany-paid medical, dental, and vision coverage for employees and eligible family membersFlexible paid time off, with a 15-day annual minimumRemote-first work environmentApplyInterested in helping organizations deploy and operate production AI infrastructure?Submit your resume and a brief introduction describing your experience with cloud architecture, AI infrastructure, or production model serving.Saturn Cloud is an equal opportunity employer. We evaluate candidates based on their qualifications and ability to contribute to the role.

Loading
Please wait..!!