PRINCIPAL SOFTWARE ENGINEER

Experis; Boston (MA); Hybrid; USD 120,000 - 160,000; Full time

Job summary

A leading technology company is seeking a Principal Software Engineer - Model Inference to join their OpenShift AI team. This role involves developing a high-performing ML inference platform and contributing to open-source communities, providing opportunities for professional growth in a collaborative environment.

Benefits

Opportunity to work on cutting-edge AI and ML technologies

Collaborative and inclusive work environment

Contribute to open-source communities

Professional growth and development opportunities

Qualifications

• Extensive experience with Python and PyTorch programming.
• Familiarity with model parallelization and memory optimization.
• Development experience with C++ is a plus.

Responsibilities

• Develop and maintain a high-quality ML inference runtime platform.
• Contribute to upstream inference runtime communities.
• Maintain CI/CD pipelines for container images.

Skills

Python

PyTorch

Model Parallelization

Quantization

Memory Optimization

C++

CUDA APIs

Job description

Our client, a leader in the technology sector, is seeking a Principal Software Engineer - Model Inference to join their team supporting the OpenShift AI team. The ideal candidate will have strong communication skills, a collaborative mindset, and a passion for innovation.

Job Title :

Principal Software Engineer - Model Inference

Location :

Raleigh, NC or Boston, MA (Hybrid)

Salary Range :

Competitive

What’s the Job?

1. Develop and maintain a high-quality, high-performing ML inference runtime platform for multi-modal and distributed model serving.
2. Contribute to upstream inference runtime communities such as vLLM, TGI, PyTorch, OpenVINO, and others.
3. Maintain CI / CD pipelines for container images to enable faster, secure, and reliable releases.
4. Coordinate with stakeholders to ensure project alignment.
5. Stay updated with AI and ML advancements to foster a growth mindset.

What’s Needed?

1. Extensive experience with Python and PyTorch programming.
2. Familiarity with model parallelization, quantization, and memory optimization using libraries like vLLM, TGI.
3. Experience with Python packaging such as PyPI libraries.
4. Development experience with C++, especially with CUDA APIs (a plus).
5. Strong understanding of model inferencing architectures.

What’s in it for me?

1. Opportunity to work on cutting-edge AI and ML technologies.
2. Collaborative and inclusive work environment.
3. Contribute to open-source communities.
4. Work with a diverse team of talented engineers.
5. Professional growth and development opportunities.

If interested, click apply now to be contacted by a recruiter. We look forward to speaking with you!

About ManpowerGroup

ManpowerGroup (NYSE : MAN) is a leading global workforce solutions company, helping organizations transform in a changing world of work. We develop innovative solutions for organizations and provide meaningful employment for millions worldwide. Our brands include Manpower, Experis, Talent Solutions, and Jefferson Wells. Recognized for diversity and ethics, ManpowerGroup has been named one of the World's Most Ethical Companies for 14 years.

J-18808-Ljbffr

Create a job alert for this search

Principal Software Engineer • Boston, MA, United States