Software Engineer (AI Infrastructure)

2 years ago

Columbia, MD, USAMid Level / Senior

Responsibilities

Design, implement, and optimize infrastructure for AI model inference at scale.
Develop and maintain production AI services and applications, including retrieval-augmented generation and autonomous agents.
Define solutions for ambiguous or underspecified systems and requirements.
Drive adoption of new technologies and practices across engineering teams.
Implement monitoring, logging, and observability for AI services.
Automate infrastructure provisioning and configuration using infrastructure-as-code principles.
Ensure high availability, reliability, and performance of AI platform components.
Contribute to security best practices for AI systems and data.
Provide technical guidance and informal mentorship to junior engineers.

At least 8 years of relevant experience, or a bachelor's degree in a technical discipline plus at least 4 years of experience.
TS/SCI clearance with polygraph.
Experience building and maintaining production systems at scale.
Experience with high-volume web application architecture and performance optimization.
Strong systems integration experience across diverse technologies and platforms.
Hands-on cloud engineering experience with AWS.
Proficiency with Kubernetes administration and deployment patterns.
Strong Python programming skills.
Experience implementing observability solutions using APM, OpenTelemetry, Grafana, and Prometheus.
Familiarity with CI/CD pipelines and DevOps practices.
Strong change management, organizational influence, communication, and collaboration skills.
Ability to work effectively in ambiguous environments and create structure where needed.
Preferred: experience with vLLM, LiteLLM, LangChain, vector databases, embedding systems, high-performance computing, or distributed systems.

501-1,000 employees