Forward Deployed Engineer AI Inference
Software Development
WFA Digital Insight
In the booming field of AI and machine learning, roles such as the Forward Deployed Engineer at Red Hat are gaining traction in the remote job market. With companies increasingly relying on AI-driven solutions, demand for professionals skilled in backend systems, Kubernetes, and production optimization has surged. In 2023, expertise in deploying large language models will be at a premium, as firms seek to harness these technologies effectively. Candidates should be prepared to showcase their deep technical abilities and agile problem-solving skills to excel in this competitive landscape.
Job Description
About the Role
Join Red Hat's vLLM and LLM-D Engineering team as a Forward Deployed Engineer. You'll play a crucial role in deploying and optimizing large language model inference systems for critical customer environments.Responsibilities
- Orchestrate Distributed Inference: Deploy and configure LLM-D and vLLM on Kubernetes clusters.
- Optimize for Production: Conduct performance benchmarks and tune parameters for latency and throughput.
- Collaborate Closely: Work alongside customer engineering teams to integrate production-quality code (Python/Go/YAML).
- Solve Complex Problems: Address challenging interactions between various models, hardware, and networking.
- Feedback Loop: Act as a liaison for core engineering to influence product development through customer insights.
Requirements
- 8+ years of experience in Backend Systems, SRE, or Infrastructure Engineering.
- Proven ability to communicate effectively regarding both systems engineering and business value.
- Strong inclination towards rapid development and prototyping.
- Comprehensive knowledge of Kubernetes.
Nice to Have
- Familiarity with multiple model architectures (MoE, etc.).
- Experience with different GPU types (NVIDIA, AMD).
Benefits
- Flexible remote work arrangements.
How to Stand Out
- Highlight your experience with Kubernetes in your resume and portfolio.
- Prepare to discuss specific challenges you've solved in past projects and the results achieved.
- Showcase any contributions to open-source projects related to backend development or AI inference.
- Understand Red Hat's focus on open-source technologies to align your interview responses with their mission.
- Be ready to discuss your approach to prototyping and problem-solving in ambiguous scenarios.
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.