Principal AI Platform and Model Operations Engineer - TS/SCI with Polygraph

GD Information Technology, Inc.; Chantilly (VA); Presencial; USD 162 000 - 219 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Health plan options

401(k) with company match

Paid time off

Flexible work options

Resumo da oferta

General Dynamics Information Technology, Inc. is actively seeking a hands-on AI Platform Operations Engineer to own and mature the end-to-end platform, moving AI workloads from development to trusted production in highly regulated environments.

You will design and operate AI/ML platform services, build controlled import/release workflows, and enforce provenance, SBOMs, license reviews, and rollback strategies across model assets and deployments.

Qualificações

• Education and active TS/SCI with Polygraph, 8+ years in platform/DevSecOps/SRE/ML engineering/cloud.
• Hands-on experience deploying local model-serving platforms (e.g., vLLM, Triton, ONNX Runtime).
• Strong Linux, containers, Kubernetes/OpenShift, networking, storage, GPU, and automation skills.
• Experience with model/artifact registries, release management, CI/CD, internal repos, and disconnected dependency management.

Responsabilidades

• Design and operate AI/ML platform services for local model serving, orchestration, registries, experiment tracking, and deployment automation.
• Build controlled import and release workflows for model weights, containers, Python packages, datasets, and vulnerability updates in disconnected environments.
• Implement provenance, SBOMs, malware/vulnerability scans, license review, approvals, staged validation, and rollback for AI artifacts.
• Deploy and tune inference services using approved serving stacks; manage batching, concurrency, memory, quantization, autoscaling, queueing, resilience, and degradation.
• Establish versioning and release relationships among model, tokenizer, prompt, retrieval index, embedding model, configuration, evaluation set, application, infra.
• Develop capacity models and advise on hardware options, cost/performance trade-offs; implement health, telemetry, and enterprise observability integration.
• Define backup/recovery, patching, vulnerability treatment, certificate rotation, and incident procedures for AI platform services.
• Partner with AI Assurance and Security to enforce gates, evaluation thresholds, audit, data restrictions, and release evidence.

Conhecimentos

Linux

Kubernetes/OpenShift

Python

CI/CD

Terraform

Ansible

Helm

GitLab CI/Jenkins

Security

Observability

Formação académica

Bachelor’s degree in Computer Science / related field

Ferramentas

vLLM

TGI

Triton

ONNX Runtime

Ollama

PyTorch

Descrição da oferta de emprego

Job Description

We are seeking a hands-on AI Platform Operations Engineer to own and mature the end-to-end platform and lifecycle mechanisms that move AI models, prompts, retrieval assets, dependencies, and services from approved development into reliable, classified production environments. This role sits at the intersection of AI engineering, cloud/platform engineering, security, data, and Service Operations, ensuring that advanced AI capabilities can be deployed and operated safely at-scale in highly regulated environments. You will be responsible for designing and managing a controlled model and software supply chain, implementing local inference services, and orchestrating repeatable release trains for AI workloads. You will establish and enforce standards for observability, capacity management, and safe rollback, operating in environments where every import, deployment, and configuration change is a governed event. This position is ideal for someone who thrives on building robust, secure, and compliant AI platforms that turn experimental solutions into mission-ready, production-grade services.

Key Responsibilities

Design and operate AI/ML platform services for local model serving, orchestration, model and artifact registries, experiment/evaluation tracking, feature or retrieval assets, and deployment automation. Build controlled import and release workflows for model weights, containers, Python packages, libraries, prompts, datasets, and vulnerability updates in disconnected environments. Implement provenance, checksums/signing, SBOMs, malware/vulnerability scans, license review, allowlists, approvals, staged validation, and rollback for AI artifacts. Deploy and tune inference services using approved serving stacks; manage batching, concurrency, memory, quantization, autoscaling where available, queueing, resilience, and graceful degradation. Establish versioning and release relationships among model, tokenizer, prompt, retrieval index, embedding model, configuration, evaluation set, application, and infrastructure. Develop GPU/CPU/storage/network capacity models and advise on hardware options, consolidation, scheduling, and cost/performance trade-offs. Implement health, latency, throughput, saturation, failure, quality, drift, and usage telemetry integrated with enterprise observability and ServiceNow. Define backup/recovery, continuity, patching, vulnerability treatment, certificate/secret rotation, and incident procedures for AI platform services. Partner with AI Assurance and Security to enforce use‑case gates, evaluation thresholds, audit, data restrictions, and release evidence. Lead technical reviews, troubleshoot production AI platform incidents, mentor engineers, and document reusable platform patterns.

Required Qualifications

Education: Bachelor’s degree in computer science, Software Engineering, Machine Learning, Information Technology, or related field, or approved equivalent experience. Location: Onsite Clearance: Active TS/SCI with Polygraph 8+ years of platform, DevSecOps, SRE, ML engineering, or cloud engineering experience, including 3+ years supporting production AI/ML platforms. Hands‑on experience deploying and operating local model‑serving platforms such as vLLM, TGI, Triton, TensorRT‑LLM, llama.cpp, Ollama, ONNX Runtime, or comparable technologies. Strong Linux, container, Kubernetes/OpenShift, networking, storage, GPU, identity, secrets, and infrastructure automation skills. Experience with model/artifact registries, experiment tracking, release management, CI/CD, internal package/container repositories, and disconnected dependency management. Ability to size inference capacity using model precision, VRAM, context length, concurrency, throughput, latency, and availability requirements. Strong Python and automation proficiency plus experience with Terraform, Ansible, Helm, GitLab CI/Jenkins, or comparable tooling. Working knowledge of RMF/STIG, software supply‑chain security, SBOMs, vulnerability management, logging/audit, and classified data handling. Demonstrated technical leadership, incident judgment, cross‑team coordination, mentoring, and clear documentation.

Preferred Qualifications

Experience with PyTorch, Hugging Face, MLflow, Kubeflow, Ray, NVIDIA GPU tooling, CUDA, or enterprise AI platform products. Experience operating A100, H100, L40S, or comparable accelerators and performing quantization/optimization. Experience with Azure Government, AWS GovCloud, C2S‑equivalent, or on‑premises platform delivery. Role‑relevant CKA/CKS, current Red Hat platform engineering credentials, or Microsoft Certified: DevOps Engineer Expert. Relevant Terraform, NVIDIA or ML‑platform credentials. Experience integrating model‑quality/evaluation signals with deployment gates and production monitoring.

Benefits

Growth: AI‑powered career tool that identifies career steps and learning opportunities. Support: An internal mobility team focused on helping you achieve your career goals. Rewards: Comprehensive benefits and wellness packages, 401K with company match, and competitive pay and paid time off. Community: Award‑winning culture of innovation and a military‑friendly workplace.

Salary

The likely salary range for this position is $161,500 - $218,500. This is not however a guarantee of compensation or salary. Rather, salary will be set based on experience, geographic location and possibly contractual requirements and could fall outside of this range.

Work Schedule & Location

Scheduled Weekly Hours: 40
Travel Required: None
Telecommuting Options: Onsite Work Location: USA VA Chantilly Additional Work Locations:

Total Rewards at GDIT

Our benefits package for all US‑based employees includes a variety of medical plan options, some with Health Savings Accounts, dental plan options, a vision plan, and a 401(k) plan offering the ability to contribute both pre and post‑tax dollars up to the IRS annual limits and receive a company match. To encourage work/life balance, GDIT offers employees full flex work weeks where possible and a variety of paid time off plans, including vacation, sick and personal time, holidays, paid parental, military, bereavement and jury duty leave. To ensure our employees are able to protect their income, other offerings such as short and long‑term disability benefits, life, accidental death and dismemberment, personal accident, critical illness and business travel and accident insurance are provided or available. We regularly review our Total Rewards package to ensure our offerings are competitive and reflect what our employees have told us they value most.

Identity Verification Process

As part of the hiring process, we will ask you to complete an identity verification process that leverages advanced biometrics and artificial intelligence to ensure authenticity and protect against identity fraud. You are expected to be on camera during virtual interviews. We reserve the right to take your picture to verify your identity and prevent fraud. By proceeding, you authorize the collection, processing, and use of your biometric data for identity verification and security purposes.

About Our Work

We are GDIT. A global technology and professional services company that delivers technology solutions and mission services to every major agency across the U.S. government, defense and intelligence community. Our 26,000 experts extract the power of technology to create immediate value and deliver solutions at the edge of innovation. We operate across 50+ countries worldwide, offering leading mission‑ready capabilities in AI, cloud, cyber and software development.

Equal Opportunity Employer

Equal Opportunity Employer / Individuals with Disabilities / Protected Veterans Opportunity Owned From working with technologies like AI, cyber and cloud to careers in intelligence and health, we offer endless opportunities to apply your expertise to create a safer, smarter world.

For more information about GDIT's Privacy Policy, click here: Privacy Policy | GDIT