Senior Software Engineer

Job Summary:

The Red Hat Performance and Scale Engineering organization is seeking a Senior Software Engineer to join our Performance and Scale for AI Platforms (PSAP) team. In this role, you will take a leading part in performance assessment and optimization of instructlab workloads and other large language models running on RHEL AI—a Generative AI-focused platform built on top of RHEL image mode technology and leveraging the open source instructlab project.

You will focus on improving performance across various aspects, including synthetic data generation, multi-phase fine-tuning, RAG stack - ingestion/similarity search, and inference benchmarking for Granite series and other open models and AI frameworks. By providing targeted optimizations and data-driven insights, you will help ensure that RHEL AI and instructlab become the go-to solutions for Red Hat’s enterprise customers who rely on a diverse range of AI hardware vendors to build Generative AI-based applications.

This position calls for a creative, adaptable engineer who is eager to learn new technologies and thrive in a dynamic, open source-oriented culture. You will be part of a centralized Red Hat performance engineering team that fosters innovation and collaboration to achieve world-class AI performance.

The broader mission of Red Hat’s Performance and Scale Engineering group is to establish performance and scale leadership across the Red Hat product and cloud services portfolio. Our scope ranges from component-level analysis to system-wide optimizations, working alongside engineering teams, product management, product marketing, and customer support, as well as Red Hat’s extensive ecosystem of hardware and software partners.

What you will do:

• Benchmarking & Analysis: Formulate performance test plans and execute performance benchmarks for various instructlab workloads and AI models. Characterize performance, drive improvements, and detect performance issues through data analysis and visualization.

• Platform Optimization: Contribute to RHEL AI platform-level optimization by targeting and measuring performance bottlenecks. Propose and implement enhancements to maximize performance across Generative AI workloads.

• Tool Development & Automation: Develop and maintain tools, scripts, and automated solutions that streamline performance benchmarking tasks.

• Collaboration & Troubleshooting: Work closely with cross-functional engineering teams to identify and address performance issues. Triage, debug, and resolve customer concerns related to instructlab and RHEL AI performance.

• Competitive Benchmarking & Knowledge Sharing: Participate in competitive performance benchmarking submissions such as MLperf. Publish results, recommendations, and best practices through internal reports, presentations, external blogs, and official documentation. Represent the team at internal and external conferences, presenting key findings and strategies.

What you will bring:

• Professional Experience: 2+ years of relevant industry experience in AI or performance engineering.

• Performance Benchmarking & Data Analysis: Proven experience in performance benchmarking, data capture, analysis, and visualization.

• AI/ML Foundations: Familiarity with core machine learning and AI concepts.

• AI Frameworks: Working knowledge of popular AI technologies and frameworks (e.g., PyTorch).

• Large Language Models: Basic understanding of LLM internals.

• Programming: Proficiency in Python with focus on data analysis and visualization coding skills.

• Linux Expertise: Hands-on experience with the Linux operating system.

• Problem-Solving Mindset: Strong passion for data-driven performance optimization and troubleshooting.

The following will be considered a plus:

• Advanced Degrees: Master’s or PhD in Computer Science, AI, or a related field.

• Profiling Tools: Familiarity with AI performance profiling and Linux system profiling tools.<