What You Will Do Collaborate with a seasoned startup and engineering team to push the boundaries of compute infrastructure. Develop software spanning our network stack, focusing on profiling and optimizing latency, reliability, and performance metrics of our checkpoint, migrate, and resume system. Gain profound insights into the physics of modern compute architecture by profiling bottlenecks in network, memory, interconnects, CPU, and GPU, understanding the hierarchy of compute architecture. Work extensively across networking stacks in low-level systems, containers, and clusters, addressing cross-node and cross-system networking challenges. Create internal tools and methodologies for simulating complex network dynamics. Build and enhance our internal storage migration system at both kernel and user space levels. Optimize network checkpointing, migration, and manipulation of network connections in flight. Requirements What We Are Looking For 3-5+ years of software development experience, particularly focusing on Linux kernel and networking stack. Exceptional articulation skills with a proven track record of documenting code and insights, fostering an environment of continuous learning and knowledge sharing. Ability to rapidly assimilate complex code bases and collaborate effectively with cross-functional teams. Strong problem-solving abilities with multidisciplinary experience. Preferred Qualifications Solid understanding of Linux and UNIX fundamentals, including standard libraries, services, networking, and kernel/user-space interaction. Proficiency in network protocols such as TCP/IP, UDP, QUIC, etc., with experience in developing and debugging on Linux using tools like gdb and valgrind. Familiarity with packet decoding and analysis tools like tcpdump and Wireshark, along with experience in developing across the stack (OS/kernel, systems, containers, services) using languages like C and C++. Experience in building data pipelines for collecting and shipping data from diverse sources, coupled with familiarity with visualization tools and frameworks. Nice to Have Knowledge of existing open-source networking technologies like eBPF, AF_XDP, Envoy, Istio, etc., and familiarity with data path hardware acceleration protocols such as RDMA and NVMe. Experience with Kubernetes, Cloud-native Network Functions, Container Network Interface plugins, performance engineering, and security practices. Passing familiarity with cross-GPU protocols like GPUDirect or NVLink. Benefits Competitive salary range: $120,000 - $170,000 per year Equity ownership in the company, providing a stake in the company's success and growth. Comprehensive health care benefits covering medical, dental, and vision. Generous vacation policy and flexible work arrangements. Access to top-tier investors and entrepreneurs, providing invaluable networking and learning opportunities. Opportunity to work on cutting-edge infrastructure for AI and High-Performance Computing, fostering continuous learning and professional growth.
