Technical Lead Engineer β Network Validation & Characterization
- Fabric
- SoCs
- Python
- InfiniBand
- Linux
- AI
Meta's Infrastructure team delivers scalable and reliable custom ASIC solutions to meet Meta's data center needs. Ramping to production and solving data center scaling and deployment challenges requires a systems-based approach to silicon bring-up and validation.
The team works on productization: early architecture and design inputs, pre-silicon validation on emulation platforms, first-silicon bring-up, and post-silicon characterization across process, voltage, and temperature corners. We write tests, build bare-metal environments and reusable frameworks that scale from pre-silicon platforms to large fleets of ASICs in the lab, and we build and maintain extensive lab automation to do it at volume and velocity.
Responsibilities
- Own the end-to-end validation and characterization strategy for Meta custom silicon programs in your domain, from pre-silicon emulation through post-silicon bring-up and PVT characterization
- Define the test plan: measurement and benchmarking methodology, instrumentation, functional and performance coverage, corner coverage across process/voltage/temperature, and pass/fail criteria
- Establish and document best practices for measurement rigor, accuracy, and correlation across bench, emulation, and ATE/production data
- Drive validation of domain feature sets (power or networking) on emulation platforms pre-silicon and on real silicon post-silicon
- Review schematics, power delivery networks, high-speed interface designs, and board/platform configurations with hardware and design teams; provide early design and debuggability inputs
- Write and review automation and analysis code that scales characterization from a single bench to many units in the lab
- Lead debug of complex cross-stack issues β silicon, firmware, driver, board, thermal, and fabric/switch layers β and drive root cause to closure with design, software, hardware, ODM, and vendor partners
- Provide technical guidance and planning for a team of validation engineers; mentor engineers and improve standards for data quality and rigor
- Partner with manufacturing, production, and data center teams to transfer characterization learnings into production screens and fleet health monitoring
Minimum qualifications
- Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
- 12+ years of relevant industry experience
- Demonstrated hands-on validation and characterization experience on complex ASICs, SoCs, NICs, or high-speed interfaces
- Proven experience with PVT (Process / Voltage / Temperature) characterization
- Ability to read and reason about schematics and either power delivery networks or high-speed interface implementations
- Proficiency in Python for test development, lab automation, and/or data analysis
- Hands-on lab experience with domain-relevant instrumentation Experience taking a custom NIC or networking ASIC from first silicon through high-volume production
- Experience working directly with ODMs and silicon/IP vendors
- Hands-on lab experience with domain-relevant instrumentation for Networking - traffic generators, protocol analyzers, high-speed scopes/BERTs, optics and cabling, switches; plus RDMA (RoCE and/or InfiniBand) at the protocol and debug level, Ethernet performance tooling (iperf, netperf, packet capture and analysis), and both front-end and back-end NICs and their differing traffic and scaling models
- Experience with Linux networking internals, kernel/userspace drivers, and DPDK or verbs-level programming
- Advanced degree (MS or PhD) in Electrical Engineering, Computer Engineering, or a related field
- Familiarity with SerDes tuning, link margining, FEC, and errata characterization
- Experience building large-scale lab automation frameworks and characterization data pipelines
- Experience with AI/HPC back-end fabrics and collective communication traffic patterns
Technical Lead Engineer β Network Validation & Characterization Β· Meta