Senior Platform Engineer - Cloud Infrastructure
Job Description
Key Skills Required
Master these to land this role
Want to know if you're a match for this job?
Qdrant is an open-source vector search engine powering the next generation of AI applications, from semantic search and retrieval-augmented generation (RAG) to AI agents and real-time recommendations.
Trusted by global leaders like Canva, HubSpot, Tripadvisor, Bosch, and Deutsche Telekom, we’re building the retrieval infrastructure layer for modern AI. Recently raising $50M in Series B funding, we are growing rapidly and committed to transforming how AI understands and interacts with data.
As a remote-first company, we believe diverse backgrounds, perspectives, and experiences fuel innovation. Here, you’ll own meaningful work, tackle challenges, and grow alongside passionate individuals dedicated to shaping the future of AI.
What you will own
- Build internal tools and services that power Qdrant Cloud infrastructure.
- Develop automation and platform components using Go and Python.
- Design systems for cluster provisioning, lifecycle management, and infrastructure automation.
- Improve Kubernetes automation through controllers, operators, and infrastructure tooling.
- Design solutions that reduce operational toil and eliminate manual infrastructure work.
- Improve reliability, scalability, and observability of the cloud platform.
- Collaborate with platform and infrastructure teams on system architecture and automation.
- Participate in incident response and implement improvements to prevent recurrence.
- Continuously improve the internal platform used to operate Qdrant Cloud.
Who you are
- 5+ years of experience in SRE, platform engineering, or infrastructure software engineering.
- Strong programming skills (Go preferred, Python acceptable).
- Experience building automation or tooling for cloud infrastructure.
- Hands-on experience operating Kubernetes in production.
- Experience working with AWS, GCP, or Azure.
- Strong understanding of Linux systems and networking fundamentals.
- Experience improving reliability through automation and systems design.
- Comfortable participating in on-call rotations.
Nice to have
- Experience building Kubernetes controllers or operators.
- Experience with Terraform or infrastructure-as-code tools.
- Experience with observability stacks such as Prometheus, Grafana, or OpenTelemetry.
- Experience operating large-scale SaaS infrastructure.
- Experience working with database or data infrastructure systems.
Why join us
- A remote-first, international team working on cutting-edge AI infrastructure.
- A competitive salary with additional perks.
- Flexible working hours and async-friendly culture.
- High ownership and real impact.
- Open-source, engineering-driven culture.
- Choose your own laptop equipment.
For US-based candidates, we also offer a comprehensive benefits package including 401k match, health, dental, and vision insurance, plus flexible PTO policy.
Qdrant is an equal-opportunity employer. We believe the best ideas come from diverse teams, and we actively welcome applicants from all backgrounds. If this role excites you but you don't check every single box, we'd still love to hear from you! We don't want to miss out on great people because of a checklist.
How would you rate this job post?
See what other professionals think about this role.
Similar Opportunities
More Openings at Qdrant
Explore Top Companies in this Space
Pila8
Data Annotation & Labeling
Learnlight
EdTech / Corporate Training / B2B SaaS
Fable Security
Cybersecurity / Human Risk Management / AI SaaS
Assort Health
HealthTech / Artificial Intelligence / Healthcare / SaaS
Qdrant
View Company ProfileQdrant (operating under qdrant.tech, legally Qdrant Berlin GmbH) is the premier, enterprise-grade open-source vector database management system, high-performance neural search engine, and similarity matching orchestration powerhouse engineered to act as the definitive, high-velocity infrastructure layer for Retrieval-Augmented Generation (RAG), large language model (LLM) persistent memory, and multimodal AI applications. Founded in 2021 by expert distributed systems and machine learning technologists Andre Zayarni and Andrey Vasnetsov, the corporate ecosystem completely eliminates the severe performance degradation, index-rebuilding latency spikes, and structural memory erosion commonly associated with legacy relational database plug-ins and primitive K-Nearest Neighbor (KNN) wrappers by building its custom storage architecture entirely from scratch in Rust. Moving far beyond traditional keyword search methods or high-latency post-filtering mechanisms, Qdrant natively unifies expansive JSON metadata payload filtering during HNSW graph traversal, native hybrid search combining dense and sparse vectors, ColBERT-based token-level late interaction reranking, and dynamic multivector storage configurations into a single high-availability data infrastructure framework. As the primary engine trusted by global developer communities and high-scale enterprise platforms, its open-source repository commands over 29,000 GitHub stars and powers critical AI pipelines for forward-thinking organizations globally. Backed by elite international venture groups, the enterprise has secured over $87 million in institutional funding—culminating in a massive Series B capital acceleration led by Spark Capital alongside 42 Capital and AVP to scale its managed Qdrant Cloud operations and native inference engine integrations. Under the hood, its technology stack harnesses advanced vector quantization strategies (including scalar and binary quantization) to execute up to a 64x memory footprint reduction with minimal recall loss, alongside real-time data indexing capabilities that expose newly added vector points instantaneously to active queries. Headquartered in Berlin, Germany, with a globally distributed remote engineering presence, the firm operates with absolute deterministic execution correctness across multi-tenant cloud and on-premise infrastructure environments. What sets Qdrant apart is its uncompromising dedication to replacing complex, multi-stage data orchestration loops with real-time, one-stage filtered similarity traversal and deep memory optimization; by bridging the gap between high-volume programmatic data repositories and millisecond-level neural vector retrieval, the corporation remains a definitive cornerstone of modern infrastructure scaling and worldwide applied artificial intelligence transformation.
Safety First
- Never pay for a job application.
- Do not share sensitive bank info.
- Verify the client before starting work.