Mid-Level AI Software Engineer [$320k/yr+] TS/SCI-FS Poly

SYSTOLIC, INC.

Annapolis Junction, MD, United States

11 days ago

Apply on www.clearancejobs.com

Prepare application

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Experienced

Compensation

$320,000.0

Working hours

Regular working hours

Job source

www.clearancejobs.com

Tech stack

Artificial Intelligence Amazon Web Services Elasticsearch Python (Programming Language) Octopus Deploy Site Reliability Engineering Practices Prometheus Large Language Models Grafana AI Platforms Kubernetes Docker

Job description

Deploy and maintain scalable inference models and infrastructure for cutting-edge Large Language Models (LLMs).
Build and maintain robust services utilizing Python, Kubernetes, Helm, and AWS cloud infrastructure.
Leverage containerization with Docker and modern inference-serving frameworks including vLLM and LiteLLM.
Implement full-stack observability and monitoring using Prometheus, Grafana, and Elasticsearch.
Provide technical leadership, guide engineering best practices, and mentor team members., * Lead the evaluation, configuration, and deployment of LLM inference models across the inference software stack.
Translate high-level stakeholder goals into scalable and reliable engineering outcomes.
Architect and maintain in-house services and techniques to ensure continuous, high-quality inference availability.
Mentor fellow engineers and foster development best practices, quality standards, and technical excellence.
Partner with cross-functional teams to establish foundational infrastructure and integrate LLM-powered capabilities.
Collaborate on surge efforts to rapidly address high-priority inference demands.
Utilize CI/CD pipelines with Argo CD and apply Site Reliability Engineering practices to maintain mission-critical AI services.