Transform research code and prototypes from our ML team into reliable, scalable solutions ready for end-user deployment
Develop applications and services in C++, Java, or Python; create gRPC-based containerized solutions with clients in Java, Python, or GoLang
Design and maintain CI/CD pipelines, ensuring smooth deployment from development to production
Configure and optimize containers using NVIDIA Triton Inference Server for high-performance inference
Profile, tune, and optimize solutions for production workloads
Create comprehensive user documentation and establish deployment best practices
Work directly with end users to understand requirements and with researchers to align development with real-world needs

Requirements

Active TS/SCI with Poly clearance
14+ years of software engineering experience
Strong programming skills in at least two of : C++, Java, Python, or GoLang
Solid understanding of DevOps practices and CI/CD pipelines
Experience with containerization (Docker) and orchestration (Kubernetes)
Experience with machine learning frameworks (PyTorch preferred)
Prior work in ML engineering or ML infrastructure
Ability to write clean, maintainable code with strong software engineering fundamentals
Experience taking projects from prototype to production
Strong communication skills for technical and non-technical audiences
Self-motivated with ability to work independently and collaboratively

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

C++JavaPythonGoLanggRPCCI/CDDockerKubernetesNVIDIA Triton Inference ServerPyTorch

Soft Skills

strong communication skillsself-motivatedability to work independentlyability to work collaboratively

Certifications

Active TS/SCI with Poly clearance