AI / LLM Platform Engineer

Responsibilities

• Design, implement, and optimize platform services such as the LLM gateway, model routing, and workflow orchestration systems.
• Develop and maintain integrations that connect LLMs to enterprise systems, data sources, and APIs.
• Identify gaps in platform capability and propose solutions.
• Conduct performance testing and validation of platform services, including prompt evaluation frameworks.
• Optimize for reliability, cost, and scalability.
• Write and deploy efficient, modular code to integrate LLMs and AI agents into enterprise systems, ensuring reliability and compatibility with existing platforms.
• Test platform changes in staging environments to evaluate performance under real-world load.
• Contribute to system-level debugging and troubleshooting.
• Collaborate with the Forward Deployed AI team, software developers, and platform architects to align platform capability with business and enterprise requirements.
• Document technical designs, workflows, and testing procedures for internal and external use. Share findings and best practices with team members.
• Explore and integrate emerging LLM providers, agent frameworks, and orchestration tools to enhance platform capabilities.
• Monitor model performance, cost, and usage; continuously optimize routing logic to balance capability vs. spend.
• Execute validation procedures and support platform compliance with CMMC, FIPS, and SNC security policy requirements.
• Implement prompt management, versioning, and evaluation frameworks to ensure AI output quality and reliability.
• Maintain platform SLOs and participate in on-call rotation for AI infrastructure.

Qualifications

• You Must Have:
• Bachelor’s degree in computer science, mathematics, applied statistics, various engineering disciplines, or related STEM discipline.
• 2+ years of experience in a related field.
• Relevant experience can be considered as a substitute for the required educational qualifications.
• In the absence of a degree, a minimum of 6 years of related experience is required.
• A higher level relevant degree may substitute for experience.
• Practical experience building and operating APIs at scale in a cloud environment (AWS, Azure, or GCP).
• Hands-on experience integrating with at least one major LLM provider (OpenAI, Anthropic, Cohere, Mistral, etc.).
• We Prefer:
• A degree in Computer Science or related field.
• Experience with generative AI models and transformer-based LLM architectures.
• Working knowledge of Agile or DevOps practices in software/ML project environments.
• Exposure to LLM orchestration frameworks such as LangChain or LlamaIndex.
• Experience with prompt engineering and evaluation frameworks.
• Familiarity with cost optimization and FinOps practices for cloud or API-based platforms.
• Familiarity with CMMC or FedRAMP compliance requirements.
• Experience with MLflow or similar experiment tracking tools.

Essential Functions

• Work extensively on a computer for coding, debugging, and integrating AI/ML systems.
• Occasionally travel to testing sites, customer locations, or conferences (up to 10-20%).
• Ability to work in a hybrid environment and manage multiple tasks effectively.

Pay & Benefits

• Estimated Starting Salary Range: $108,496.89 - $149,183.22.
• SNC offers a generous benefit package, including medical, dental, and vision plans, 401(k) with 150% match up to 6%, life insurance, 3 weeks paid time off, tuition reimbursement, and more.