Software Engineer – AI/ML & High Performance

Benz Technology; Fort Meade (MD); On-site; USD 150,000 - 190,000; Full time

Job summary

Benz Technology is seeking an AI/ML inference engineer to join a team focused on high-performance GPU-accelerated applications in a cloud environment. You will develop AI/ML models, deploy cloud infrastructure with Terraform on AWS, and work with large streaming datasets for real-time processing.

The role requires proficiency in C++, Python, or Golang and experience building latency-sensitive systems, with a focus on scalable streaming analytics.

Qualifications

• AI/ML development or integration experience.
• Terraform on AWS.
• Proficiency in C++, Python, and/or Golang.
• GPU-enabled / high-performance application development.
• Large-scale streaming data analytics.

Responsibilities

• Develop and integrate AI/ML models into production inference pipelines.
• Build and deploy cloud infrastructure using Terraform on AWS.
• Write high-performance, GPU-enabled applications for real-time processing.
• Design and maintain large-scale streaming data analytic systems.
• Contribute across the stack using C++, Python, and/or Golang.
• Optimize application performance for latency-sensitive workloads.

Skills

AI/ML development

GPU programming

Latency optimization

Streaming analytics

Tools

Terraform on AWS

Docker

Kubernetes

Job description

Active TS/SCI security clearance required. Benz Technology is unable to sponsor clearances.

U.S. citizenship required.

About the Role

You will join an inference processing team focused on building and integrating high-performance AI/ML capabilities. This role involves developing GPU-accelerated applications and working with large-scale streaming data pipelines in a cloud environment.

Responsibilities

• Develop and integrate AI/ML models into production inference pipelines
• Build and deploy cloud infrastructure using Terraform on AWS
• Write high-performance, GPU-enabled applications for real-time processing
• Design and maintain large-scale streaming data analytic systems
• Contribute across the stack using C++, Python, and/or Golang
• Optimize application performance for latency-sensitive workloads

Required Qualifications

• AI/ML development or integration experience
• Terraform on AWS
• Proficiency in C++, Python, and/or Golang
• GPU-enabled / high-performance application development
• Large-scale streaming data analytics

Desired Qualifications

• Experience with inference optimization frameworks (e.g., TensorRT, ONNX)
• Familiarity with containerization and orchestration (Docker, Kubernetes)
• Experience with Apache Kafka or similar streaming platforms