141 jobs for “Storage Software Engineer - Python / Lin”
Nebius London
Builds and operates a multi-tenant distributed data platform based on YTsaurus, writing core C++ for storage, scheduling and dynamic tables. Works end-to-end on platform features, performance and reliability, including on-call, with Go and Python for services and tooling.
Nebius London
Builds and evolves the open-source YDB platform, a distributed storage and relational database system spanning tens of thousands of nodes and hundreds of petabytes. Work includes redesigning core components for QLC NVMe, 800 Gb/s NICs, Arm-based NVIDIA GB300 hosts and SMR HDDs, plus erasure coding, recovery and silent-corruption prevention. Merged changes typically reach production clusters within weeks.
Amazon Thames Valley, Berkshire, GBR
Oversees physical security across a cluster of AWS data centres, directing Security Officers and auditing documentation, technology and processes. Leads cross-functional projects to close security gaps, standardise governance frameworks and raise standards across high-security sites. Requires UK national status and ability to obtain UK Government Security Clearance.
Amazon London
Owns end-to-end delivery of external water infrastructure for AWS data centres across EMEA, from scoping and design through permitting, procurement, contracting and construction. Manages third-party design consultants, budgets, business cases and Capital Allocation Requests, and negotiates infrastructure agreements with utilities, regulators and contractors. Distinct for its blend of technical design competency, project management and programmatic leadership across legal and procurement.
Nebius London
Builds and operates large-scale indexing systems and data pipelines for an agent-native search platform, handling tens of gigabytes per second across petabyte-scale datasets. Focuses on storage formats, compaction, freshness, observability and cost optimisation, working with Go alongside runtime and ML teams.
Nebius London
Builds and operates low-latency, high-throughput runtime services for an agent-native search platform, handling thousands of requests per second under strict latency budgets. Work spans query processing, retrieval orchestration and response assembly, with heavy focus on CPU, memory and data-access optimisation, observability and reliability. Collaborates with indexing and ML teams to integrate retrieval and ranking while keeping ML logic decoupled from core internals.
Nebius London
Builds and owns core components of a GPU-native serverless AI platform, spanning control plane, scheduler, runtime, autoscaler and customer-facing APIs. The role is end-to-end and high-ownership, tackling cold-start latency, GPU scheduling under contention, multi-tenant isolation and edge request routing while running the service with SRE practices.
Nebius London
Builds and operates web-scale crawling and ingestion infrastructure for an agent-native search platform, handling billions of URLs with a focus on coverage, freshness and reliability. Involves crawl scheduling, URL discovery, deduplication, content extraction and observability, working closely with indexing and ML teams.
Nebius Amsterdam, Netherlands; Germany; United Kingdom
Builds and operates a production Managed PostgreSQL service for AI workloads, spanning Go control-plane automation, Postgres internals tuning, and migration tooling off RDS, Cloud SQL and self-managed clusters. Also drives vector search (pgvector) and runs the service like an SRE, handling SLOs, incidents and customer escalations.
Nebius London
Develops and extends the QEMU/KVM virtualization stack, optimising I/O for emulated disk and network devices, distributing resources between VMs and hardening the hypervisor against untrusted code. Works closely with the open-source community on upstream patches, with a focus on low-level security and performance.
Nebius Amsterdam, Netherlands; Berlin, Germany; United Kingdom
Lead the mk8s Core team building a managed Kubernetes service on Nebius cloud, owning the API, control plane, cluster autoscaling and platform integrations. The role is hands-on: you write and review Go code, lead projects and join on-call, while managing 4-8 engineers and shaping technical vision with product. Work targets scaling to tens of thousands of GPU nodes across 10+ data centers.
Nebius Chertsey
Hands-on role maintaining and optimising IT infrastructure in a GPU cloud data centre, covering server and network hardware diagnostics, installations, upgrades, decommissioning, and fibre optic and patch cabling. Involves shift work Friday to Monday across day and night shifts, plus possible travel between sites and on-call rotations.
Nebius London
Hands-on role maintaining and optimizing IT infrastructure in a data center, working with advanced H200 GPU cloud clusters. Responsibilities include diagnosing server hardware issues, installing and dismantling hardware, managing fiber optic connectivity, processing RMAs, and writing configuration documentation while collaborating with internal teams and contractors.
Nebius Finland; France; Germany; Netherlands; Remote - Europe; Spain; Sweden; United Kingdom
Lead and scale a customer-facing Solutions Architecture organisation across EMEA, partnering with regional Sales leadership to define coverage, operating models and performance expectations. The role combines people leadership and hiring with direct engagement on strategic customer opportunities, spanning cloud-native infrastructure, Kubernetes, GPU workloads and AI/ML deployments.
Nebius Harlow
Hands-on role maintaining and optimising IT infrastructure in a GPU cloud data centre, covering server and network hardware troubleshooting, installations, upgrades, decommissioning, and fiber optic and patch cabling. Involves shift work (day and night), on-call rotations, RMA handling, and possible travel between data centres.
