Systems Software Engineer - Object Storage

LT ZERO Asia Pacific•Centennial, CO

7h•$130,000 - $170,000•Hybrid

About The Position

Quantum is seeking a Senior Object Storage Software Engineer to design, implement, and optimize the object storage data path and core distributed services of their scale-out object storage platform. The role involves owning software from network interface request handling through processing, metadata operations, data placement, and durable persistence across the cluster. This is a deep systems role for engineers passionate about low-latency code paths, high concurrency, and distributed systems correctness at scale.

Requirements

12+ years of software development experience using C/C++, Rust (or equivalent systems-level expertise).
Strong experience with distributed systems and high-performance storage software design.
Strong Linux experience, including debugging, profiling, and performance analysis of complex systems.
Solid understanding of concurrency, locking, and asynchronous programming models.
Strong communication skills; ability to collaborate in a team environment and across functions; ability to work effectively with remote teams.
Self-motivated, able to identify and solve problems independently, creative problem-solving mindset.
Willing and able to come to our office in Centennial, CO during core business hours (Tuesday - Thursday 10am-4pm).

Nice To Haves

Experience with the Linux I/O subsystem and networking (plus).
Experience with storage protocols, clustering design and development (plus).
Experience with containers and Kubernetes (plus).
Experience using Git and Jira.
Experience with Amazon AWS S3 API, SDK’s & Tools.
Experience with AI tools or programming is a plus (especially for modern data pipelines and workload integration).

Responsibilities

Design and optimize the object request pipeline for PUT/GET/DELETE and background operations, focusing on predictable latency, high throughput, and efficient CPU/memory usage in the critical path.
Build and maintain data path components such as request parsing/validation, routing, throttling, buffering, streaming I/O, and zero-copy / reduced-copy transfers where applicable.
Implement and tune distributed caching (read cache / metadata cache) and request coalescing strategies to reduce backend amplification and improve tail latency.
Identify and eliminate bottlenecks end-to-end (network → CPU → storage), leveraging deep Linux profiling and systems debugging skills.
Architect and evolve scale-out services for object metadata, namespace/indexing, placement, and cluster membership/state required for large clusters.
Design and maintain scalable, high-performance components such as metadata management and data placement algorithms across multi-node deployments.
Implement and maintain durability features such as erasure coding, replication, background healing, snapshots (where applicable), thin provisioning concepts, and data scrubbing to deliver “six nines” class durability.
Ensure correctness under failures: node loss, disk faults, partial writes, network partitions, and rolling upgrades—without compromising data integrity.
Solve high-concurrency challenges in the object and metadata paths using robust synchronization strategies, lock minimization, and asynchronous execution models to maximize multi-core CPU utilization.
Apply careful correctness reasoning around ordering, idempotency, and race conditions in distributed request flows.
Ensure the object data path and background systems scale linearly as nodes are added, including rebalancing and reconstruction workflows that minimize customer-visible impact.
Collaborate cross-functionally to integrate other platform components into the solution and operate effectively with remote teams.