Software Engineer 2 (Hybrid)

About the role

ML Deployment Engineer moves video, image, speech, and text analytics (VISTA) models from research prototypes to production inference services that downstream engineering teams can run in Kubernetes or similar environments. You will work individually or as part of a small research/SDK team.

Responsibilities

• Collaborate cross-functionally working directly with end users to understand requirements and with researchers to align development with real-world needs.
• Build the CI/CD and packaging around Python on NVIDIA Triton Inference Server, with TensorRT execution providers and Business Logic Scripting (BLS) in-service pipelines.
• Tune pipelines for throughput, and support them through customer transition.
• Create comprehensive user documentation and establish deployment best practices.
• Resolve system problem reports and contribute to system design, including hardware/software trade-offs, software reuse, infrastructure-as-code, and requirements analysis from the system level down to individual components.

Requirements

• TS/SCI with agency appropriate polygraph.

Qualifications

• Bachelor’s Degree in Computer Science or a related discipline.
• 14+ years of software engineering experience.
• Four (4) years of additional software development experience on comparable projects may be substituted for a bachelor's degree.

Technical Skills

• Strong Python experience.
• Solid understanding of DevOps practices and CI/CD pipelines.
• Intermediate/Advanced experience with containerization (Docker).
• Beginner/Intermediate experience with orchestration tools such as Kubernetes.
• 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.

Desired Technical Skills

• Software Development experience: C++, Java, GoLang, CUDA.
• Experience supporting production ML systems.
• Familiarity with ML domains: Natural Language Processing, Computer Vision, Automated Speech Recognition, or Video Processing.
• Knowledge of model formats and optimization (ONNX, TensorRT).

Benefits

• Wyetech automatically contributes 20% of each employee's gross compensation to a Simplified Employee Pension (SEP) IRA, with no requirement for employee matching.
• Full-time employees have the option to participate in a variety of voluntary benefit plans including: A Choice of Medical Plan Options, some with Health Savings Account (HSA), Vision and Dental, Life and AD&D Benefits, Short and Long-Term Disability, Hospital Indemnity, Accident, and Critical Illness Insurances, and optional Identity Theft and Legal Protection Services.
• Employees receive two complementary branded clothing orders annually.
• Company Environment & Perks: Monthly lunches, summer company picnic, and an annual holiday party.

Pay and Schedule

• $64.04 - $120.27 an hour Pay Range.
• Hourly pay rates listed for this position serve as a general guideline and are not a guarantee of compensation.

Benefits Package

• Wyetech provides a generous PTO plan of up to 200 hours annually, aligned with applicable state leave regulations.
• The company offers a Choice of Medical Plan Options, some with Health Savings Account (HSA), Vision and Dental, Life and AD&D Benefits, Short and Long-Term Disability, Hospital Indemnity, Accident, and Critical Illness Insurances, and optional Identity Theft and Legal Protection Services.
• Employees have the flexibility to adjust their PTO allocation at the start of each calendar year, ensuring it meets their evolving needs.
• Full-time employees have the option to participate in a variety of voluntary benefit plans.
• Wyetech, LLC is an Equal Opportunity Employer.
• Affirmative Action Statement: Wyetech, LLC is committed to the principles of affirmative action in all hiring and employment for minorities, women, individuals with disabilities, and protected veterans.