Senior AI Platform Engineer
About The Position
The Senior AI Platform Engineer is responsible for building and operating the infrastructure that powers Venture Global's AI Engineering function. This role designs, stands up, and maintains the compute, serving, and tooling foundation for AI agents and machine learning systems across both cloud and secure on-premises environments, with on-premises infrastructure driven by data residency and security requirements. The Senior AI Platform Engineer owns the deployment and optimization of self-hosted open-weight large language models, GPU infrastructure, and the platform services that enable engineers to build and ship reliably and securely. This role works closely with the Principal AI Engineer on architecture, with Data Engineering on data and platform integration, and with IT and security teams to ensure a hardened, well-governed environment. The measures of an ideal candidate include infrastructure expertise, operational rigor, automation mindset, security awareness, collaboration, and a strong bias for reliability. This new position will be based in our Arlington, VA headquarters and report to the Director of AI Engineering.
Requirements
- 7+ years of experience in infrastructure, platform, DevOps, or machine learning engineering.
- Bachelor's degree in Computer Science, Engineering, Mathematics, or related field of study.
- Hands-on experience deploying and operating GPU infrastructure for AI/ML workloads, on-premises and/or in the cloud.
- Experience serving and optimizing large language models, including familiarity with inference/serving frameworks and optimization techniques (e.g., quantization, batching).
- Strong proficiency with cloud platforms and containerization/orchestration technologies.
- Proficiency in Python and infrastructure-as-code tooling.
- Experience building CI/CD pipelines and implementing MLOps/LLMOps practices.
- Solid understanding of security, networking, and access control in enterprise environments.
- Strong troubleshooting skills and operational discipline for maintaining reliable production systems.
- Excellent interpersonal and communication skills, with strong critical thinking and attention to detail.
- Strong work ethic with the ability to effectively prioritize, meet deadlines, adapt to changing priorities, and succeed in a fast-paced environment.
Nice To Haves
- Experience with LLM serving frameworks such as vLLM, TGI, TensorRT-LLM, or similar.
- Experience with Databricks and streaming data platforms such as Kafka.
- Experience with on-premises AI infrastructure in environments with data residency or security constraints.
- Experience deploying infrastructure in or adjacent to operational technology (OT), industrial, or safety-critical environments.
- Familiarity with agent frameworks and their deployment/runtime requirements.
- Experience with GPU cluster management, scheduling, and utilization optimization.
- Experience utilizing DevOps/MLOps tooling and observability stacks.
- Strong technical writing skills.
Responsibilities
- Design, build, and maintain AI infrastructure across cloud and on-premises environments, including GPU compute clusters.
- Deploy, serve, and optimize self-hosted open-weight LLMs, applying techniques such as quantization, batching, and inference optimization to maximize throughput and minimize latency and cost.
- Build and operate the platform services, pipelines, and tooling that enable AI engineers to develop, test, and deploy agents and models reliably.
- Implement scalable serving infrastructure supporting both batch and streaming inference workloads.
- Establish and maintain MLOps/LLMOps capabilities, including model registries, CI/CD for models and agents, monitoring, observability, and automated deployment.
- Support procurement of GPU servers and AI infrastructure by defining specifications, benchmarking hardware, and validating capacity plans.
- Harden the AI platform in partnership with IT and security teams, implementing appropriate segmentation, access controls, and governance.
- Integrate AI platform infrastructure with enterprise data systems, including Databricks and streaming platforms.
- Automate infrastructure provisioning and configuration using infrastructure-as-code and modern DevOps practices.
- Monitor platform performance, reliability, and utilization; troubleshoot and resolve infrastructure and serving issues.
- Contribute to architecture and design decisions alongside the Principal AI Engineer and Director of AI Engineering.
- Document platform architecture, runbooks, and operational procedures for maintainability.
Benefits
- Equal Opportunity Employer
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
