The Role
Openchip is building exciting new RISC-V chips with AI and HPC acceleration. As a Junior Performance Software Engineer, you will actively participate in our performance team, helping to optimize popular AI and HPC applications and benchmarks to deliver best-in-class performance, and work with customers to optimize their workloads.
Key Responsibilities
1. Make independent technical contributions to help their team deliver its commitments. In particular:
2. Optimize AI, HPC, and other workloads and benchmarks for our RISC-V silicon with vector extensions.
3. Identify bottlenecks with workload characterization and drive implementation of solutions.
4. Decompose applications and analyze how they run on the underlying hardware.
5. Understand performance at a system level, including CPU, memory, storage, and power utilization.
6. Profile and optimize on our pre-silicon environments (simulators, emulators, FPGAs) and silicon environments.
7. Troubleshoot and perform root cause analysis to resolve performance issues.
8. Optimize HPC and AI libraries and runtimes.
9. Work with customers to optimize their workloads for our architecture.
10. Contribute to instrumentation of performance and power at the OS level.
11. Integrate with CI/CD pipelines to automate performance benchmarking.
12. Present findings to senior technical leaders within the company and at industry conferences.
13. Contribute upstream where appropriate.
14. Interact with colleagues across projects to unblock issues or reach consensus on technical topics:
* Work with hardware teams, influencing hardware/software co-design.
* Collaborate with teams developing compilers, firmware, AI stacks, middleware, etc.
* Participate in code reviews, bug triaging, and design document discussions.
* Contribute to shared team responsibilities like CI failure triaging, documentation, and code fixits.
1. Qualifications
2. Bachelor's or Master’s degree in a relevant field.
3. 1-3 years of experience in the relevant field.
4. Solid knowledge of computer architecture (CPU, cache, memory hierarchy, buses, etc.).
5. Proven experience with performance optimization and profiling tools (Linux perf, iperf, lmbench, sysbench, flamegraphs, JMeter, LoadRunner, Gatling, Intel VTUNE, ARM SPE, etc.).
6. Strong knowledge of low-level development languages (C, C++, Rust, etc.).
7. Experience with assembly language (any architecture).
8. Experience with performance benchmarks (CoreMark, FPMark, LMBench, Stream, SPEC CPU, SPEC INT, etc.).
9. Understanding of operating systems, databases, networking, and cloud technologies.
10. Strong problem-solving skills for troubleshooting complex issues.
11. Experience with bare-metal development for embedded systems and microcontrollers.
12. Proficiency with source control (git), CI tools, and task management (Jira).
13. Experience with machine learning and HPC performance optimization.
14. Experience with Fortran, RISC-V assembly, statistical analysis, emulators, simulators (Qemu, Gem5, Spike), containerization (Docker, Kubernetes), hypervisors (KVM, Xen), and open source software development.
Soft Skills
* Team-oriented: communicative and collaborative, focusing on team outcomes.
* Curious about learning new technologies and stacks.
* Capable of within- and cross-team technical collaboration.
* Proactive, self-motivated, and willing to overcome obstacles.
We are looking for outstanding individuals willing to join our mission to change the industry and build a better world.
If you identify with Openchip, please contact us. We offer a competitive compensation package and flexible work arrangements to help you balance personal and professional life.
At Openchip & Software Technologies S.L., we believe a diverse and inclusive team fosters groundbreaking ideas. We promote a work environment where everyone feels valued, respected, and empowered to reach their full potential—regardless of race, gender, ethnicity, sexual orientation, or gender identity.
#J-18808-Ljbffr