AI Platform Engineer

Meitner Energy; United States; On-site; USD 140,000 - 190,000; Full time

Job summary

Meitner Energy is seeking an MLOps and AI Platform Engineer to deploy, operate, and continuously improve the model-serving layer of the company’s private AI platform. This is a hands-on role focusing on configuring serving infrastructure, owning gateway and routing logic, building pipelines and automated tests, and running model evaluation for production deployment.

You will work directly with the AI Platform Lead, own CI/CD and test strategy, and ensure platform reliability in a regulated

Qualifications

• Bachelor's degree in computer science, engineering, or related technical discipline or equivalent experience.
• 3+ years in MLOps/platform/infrastructure engineering with ML/LLM focus.
• Hands-on experience deploying high-throughput model-serving for LLMs, incl. quantization trade-offs.

Responsibilities

• Deploy and operate high-throughput model-serving infrastructure and tune GPU memory planning.
• Own gateway and routing logic, including token accounting and model version pinning.
• Own CI/CD pipelines, automated tests, and release gates for the platform.

Skills

MLOps

Platform engineering

Python

Containers

Kubernetes

CI/CD

Inference tuning

Gateway routing

GPU memory management

On-site Dallas

Education

Bachelor's degree in CS/Engineering

Tools

IaC (infrastructure as code)

Job description

Meitner Energy is seeking an MLOps and AI Platform Engineer to deploy, operate, and continuously improve the model-serving layer of the company’s private AI platform. This is a hands-on engineering role: the successful candidate will personally configure and tune serving infrastructure, own gateway and routing logic, build the pipelines and automated tests that keep the platform reliable, and run the evaluation process that determines which models reach production. The position suits a platform or infrastructure engineer with real production LLM serving experience who wants to build rather than maintain.

About Meitner Energy

Meitner Energy is developing advanced nuclear energy solutions intended to deliver reliable, scalable, and carbon-free electricity for industrial and grid applications.

Our international team brings together nuclear, engineering, commercial, regulatory, and project-development experience. We are building an organization focused on disciplined engineering, responsible execution, and the deployment of nuclear energy at meaningful scale.

The Opportunity

Meitner’s AI platform is being built now, and this role is one of the hands that builds it. You will deploy and operate the model-serving lanes, own the gateway and routing logic that sits in front of them, and run the model evaluation and promotion process that determines what the organization actually uses. The role also carries designated ownership of continuous integration, delivery, and test strategy for the platform, which means the pipelines and quality gates that protect it are yours to design and hold.

The work is technical and consequential. Model-serving decisions affect engineers and operators who use the platform daily across the company’s sites, working on material that includes export-controlled nuclear technology. You will work directly with the AI Platform Lead and operate with significant autonomy over your area of the platform.

This role is ideal for someone who:

• Wants to build and operate a production LLM platform rather than maintain one that is already finished.
• Takes real ownership of reliability: writes tests, enforces gates, and does not ship work they are not confident in.
• Is fluent across the modern platform stack, including Python, containers, container orchestration, and high-throughput model serving, and can move quickly without cutting corners.
• Finds the intersection of high-performance inference and security-conscious regulated environments interesting rather than frustrating.

What You'll Do

Model Serving and Inference

Deploy, configure, and tune high-throughput model-serving infrastructure, managing quantization strategy and GPU memory planning so that target models fit the available hardware within budget. You will monitor inference latency, throughput, and utilization, identify and resolve bottlenecks across the serving stack, and support capacity planning and infrastructure sizing decisions alongside the AI Platform Lead.

Gateway, Routing, and Platform Reliability

Implement and maintain the gateway and router rules that govern access to the platform, including token accounting, prompt-injection defenses, model version pinning, and request routing between regulated and non-regulated serving tiers. You will manage controlled model promotion and rollback so that platform state remains auditable and reversible, and contribute to the platform’s security posture by supporting data-sensitivity routing and export-control requirements in the design of every change you make.

Continuous Delivery, Testing, and Engineering Standards

Own the continuous integration and delivery pipelines for platform code, and establish the automated test coverage and quality gates that enforce the standards set by the AI Platform Lead. You will hold primary responsibility for pipeline architecture, release governance, and test strategy for the platform, participate in code review for platform-layer changes, and document decisions clearly enough that another engineer can operate what you build.

Run structured comparisons across candidate open-weight and proprietary models using the evaluation harness owned by the AI Platform Lead, covering generation and embedding models alike. You will document results clearly, surface regressions, and contribute model selection recommendations supported by evidence rather than impression.

What We're Looking For

Required Qualifications

• Bachelor’s degree in computer science, engineering, or a related technical discipline, or equivalent professional experience.
• 3+ years of professional experience in MLOps, platform engineering, or infrastructure engineering with a focus on machine learning or LLM systems.
• Hands-on production experience deploying and operating a high-throughput model-serving framework for large language models, including quantization trade-offs you can explain and defend.
• Proficiency in Python, containers, and production container orchestration, with the ability to debug a serving outage, trace a gateway misconfiguration, and read infrastructure-as-code confidently.
• Experience building and maintaining continuous integration and delivery pipelines with automated testing and release gates.
• Working knowledge of inference performance tuning, GPU memory constraints, and gateway or routing frameworks for model access.
• Ability to work on-site in Dallas.

Preferred Qualifications

• Working proficiency in Spanish. Spanish is preferred because the position involves technical collaboration with colleagues in Argentina.
• Experience operating in security-sensitive or regulated data environments, including export-controlled or controlled unclassified information settings.
• Exposure to retrieval pipeline implementation and embedding model deployment.
• Background in nuclear energy, defense, aerospace, or another regulated industrial sector.

The Candidate We Are Seeking

The strongest candidate will be an engineer who has put a model-serving platform into production and kept it running. This may be an excellent next step for a platform engineer, MLOps engineer, or infrastructure engineer who wants a defined area of a new platform to own outright. Candidates should be prepared to discuss deployments they personally configured, tuned, broke, and repaired.