Junior Software Engineer – Inference

Neuralsolutions; Columbia (MD); On-site; USD 138,000 - 163,000; Full time

Job summary

Neuralsolutions in Columbia, MD seeks a Software Engineer to support AI infrastructure, ensuring access to high-quality LLMs across the inference stack. You’ll procure, configure, and test models, develop in-house services, and collaborate with model vendors to maintain reliable pipelines for customer-facing AI capabilities.

The role emphasizes building scalable infrastructure, working with AWS and containerized environments, and contributing to production-grade AI hosting practices.

Qualifications

• Proficiency in Python or similar languages.
• Experience with Argo CD and CI/CD workflows.
• Hands-on with Kubernetes (Kubernetes/Helm).
• Cloud experience with AWS or similar.
• Ability to learn new technologies quickly.
• Strong communication skills and teamwork.

Responsibilities

• Procure, configure, and test new inference models for release to users.
• Develop in-house services to guarantee high-quality inference services.
• Collaborate with model vendors to create reliable closed-source pipelines.
• Support surge efforts for short-term, high-priority inference needs.
• Work with other teams to build infrastructure and integrate LLM tools.

Skills

Python

Argo CD

Kubernetes

Helm

AWS

Learning agility

Communication

Education

Bachelor's degree in a technical discipline

7 years of experience without degree

Tools

Docker

Job description

Software Engineer - AI Infrastructure

We’re seeking a software engineer to support our AI infrastructure team at Columbia, MD. In this role, you’ll help build and maintain the foundation for customer AI capabilities while supporting a broader ecosystem of AI-enabled applications. Your focus will be ensuring access to the highest available quality LLMs to users throughout the inference software stack.

Responsibilities:

• Procure, configure, and test new inference models, preparing them for release to our user base.
• Develop in-house services and techniques to guarantee continual high-quality inference service for our customer.
• 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 from our customer.
• Engage with other teams in our organization to establish solid infrastructure for our services and integrate LLM-powered tools for user needs.

Required Skills:

• Experience with Python and/or other modern programming languages.
• Familiarity with Argo CD and/or other CI/CD frameworks.
• Experience with Kubernetes/Helm.
• Familiarity with AWS or other cloud service providers.
• Ability to learn new technologies quickly.
• Strong communication skills and willingness to ask questions.

Nice to Have:

• Experience with vLLM, LiteLLM, or similar inference-serving frameworks.
• Experience with other LLM hosting frameworks and practices.
• Experience supporting production software using Site Reliability Engineering (SRE) best practices.
• Experience with Elastic, Grafana/Prometheus, or other observability frameworks and practices.
• Experience with Docker and containerization.
• Experience in traffic shaping and quality-of-service engineering.
• Knowledge of and interest in hosting AI capabilities.

Experience Required: 3 years with Bachelor's degree in a technical discipline or 7 years without degree

Location: Columbia, MD

Clearance: TS/SCI with Polygraph required

Salary Range: $138,000 - $163,000

Questions about this role or want to learn more about Neural Solutions?