Sr. Object Storage Architect, Autopilot Infrastructure

Recruiter
Tesla
Location
Fremont, California
Salary
Competitive
Posted
13 Oct 2018
Closes
15 Nov 2018
Ref
73244
Sector
Engineering
Category
Design
Contract Type
Permanent
Hours
Full Time
The Role:

The candidate will be a key technical member of the Autopilot Infrastructure team responsible with designing evolving storage and data solutions. They will join a team of experts in researching and developing innovated ML/CV workloads and cluster technologies including heterogeneous compute nodes, networking and multi-tiered storage. As we continue to innovate with compute and scale data ingest, the storage infrastructure must evolve to complement requirements.

Responsibilities:
  • Continue to optimize and scale current multi-tiered cluster storage design. Ensure sizing of each component reflects the developing characteristics of data and workload.
  • Work with engineers to ensure dataset is structured in an optimized format support significant scale with both data and metadata.
  • Architect and implement multi-site, multi-region, on-premise object storage.
  • Analyze all storage workloads and identify performance bottlenecks and opportunities
  • Architect and implement world-wide data ingest reflecting connectivity characteristics, privacy, relevancy ratings, and governmental policies.
  • Research emerging technology NVMe/QLC standards and map to optimal implementation and help develop IP for high performance networked storage
  • Work collaboratively with team responsible for SoC level system modeling to explore relevant SoC architectures
  • Propose and execute on innovations in both software and hardware architecture based on the benefits to high-speed, large-scale applications.

Requirements:

The candidate must have both excellent technical and communication skills. Because the workload is quickly evolving, the requirements and architecture must continually be coordinated with the Autopilot Data Scientists. Additionally:
  • B.S., M.S., or Ph.D. in Computer Engineering or Electrical Engineering and at least 8 years of engineering and architecture experience
  • Demonstrated record of designing and delivering complex and high-performance systems and high-density storage using flash. Strong NVMe experience
  • A track record of successful validation experience in storage domains such as Block, File and/or Object storage
  • Exposure and understanding of storage workloads and benchmark performance
  • Experience analyzing storage workloads
  • Experience with datacenter infrastructure (Cluster management, virtualization, containers, etc.)
  • Validation expertise and experience in the following storage technologies: RAID, Storage Virtualization, Distributed block devices, Snapshots/Clones, Thin Provisioning, Storage management
  • Strong knowledge of Python, Go, Perl, test automation frameworks
  • Good understanding of standards-based storage management standards such as DMTF Redfish/Swordfish and validation of management infrastructures
  • Good knowledge of test strategies for cloud topologies like hyperconverged and hyperscale cloud storage
  • Experience of validation through automation of storage controller arrays, cloud storage stacks
  • Knowledge of modern storage technologies and associated network interconnect technologies specifically: RDMA, ROCEv2, InfiniBand
  • Knowledge of Flash translation layer; LBA, wear levelling, GC, write amplification, etc.
  • Storage interfaces and protocols. Solid experience in PCIe and NVMe interfacing and understanding of I/O protocols

Similar jobs

Similar jobs