AI Inference Software Engineer — TS/SCI On-Site

Intezra, Inc.; Columbia (MD); On-site; USD 130,000 - 160,000; Full time

Benefits offered by this job

CareFirst medical plans

Dental and Vision coverage

401(k) 15% contribution

PTO: 160 hours

Floating holidays

Code Red Days

Job summary

Intezra, Inc. is seeking a Software Engineer — AI Inference in Columbia, MD to help build and sustain AI infrastructure and inference services.

You will focus on delivering high-quality LLM access across the inference stack while adapting to evolving technologies and requirements. The role emphasizes collaboration with model vendors, internal teams, and customers to support AI-enabled applications, with a strong emphasis on reliability, scalability, and rapid problem solving in a

Qualifications

• 3+ years with a Bachelor's degree, OR
• 4 additional years of relevant experience in lieu of a degree

Responsibilities

• Procure, configure, and test new inference models, preparing them for release to the user base.
• Develop in-house services and techniques to guarantee continual high-quality inference service for customers.
• Work with model vendor teams and representatives to create reliable pipelines for closed-source model usage.
• Collaborate with teammates on surge efforts to support short-term, high-priority inference needs.
• Engage with other teams in the organization to establish solid infrastructure for services and integrate LLM-powered tools for user needs.

Skills

Python

Argo CD

Kubernetes

AWS

Learning agility

Communication

Education

Bachelor's degree

Tools

Docker

Helm

CI/CD tooling

Job description

Intezra, Inc. is seeking a Software Engineer — AI Inference in Columbia, MD to help build and sustain AI infrastructure and inference services.

You will focus on delivering high-quality LLM access across the inference stack while adapting to evolving technologies and requirements. The role emphasizes collaboration with model vendors, internal teams, and customers to support AI-enabled applications, with a strong emphasis on reliability, scalability, and rapid problem solving in a