Member of Technical Staff – AI Inference platform, robustness

ph3Member of Technical Staff – AI Inference platform /h3 pFull-time /p h3Your mission /h3 pYou will make Lyceum's AI inference platform reliable, secure, and scalable
- ensuring it performs under pressure as we grow to thousands of concurrent users. While others on the team expand what the platform can do, your job is to make sure it keeps working, fails gracefully, and gets faster over time. /p h3Your focus /h3 ul liScalability: Architect and implement the systems that allow our inference platform to scale to thousands of concurrent users. This includes request routing, load balancing, autoscaling, and resource scheduling across GPU clusters. /li liReliability and observability: Build robust monitoring, alerting, and incident response tooling. Design for graceful degradation, automatic recovery, and minimal downtime. /li liPerformance engineering: Profile and optimise the full inference path from request ingestion through model execution to response delivery. Identify and eliminate bottlenecks at every layer. /li liInfrastructure evolution: Evaluate and integrate open-source inference frameworks and tooling (Dynamo, vLLM, Triton, etc.) where they improve throughput, latency, or stability of the serving stack. /li /ul h3Your KPIs /h3 ul liPlatform uptime and availability (SLA adherence) /li liP50/P95/P99 latency and throughput under load /li liTime-to-detection and time-to-resolution for incidents /li liScalability milestones (concurrent users, requests per second, GPU utilisation) /li /ul h3Your profile /h3 pWe consider candidates from diverse backgrounds, with a deep love for technical challenges and the desire to take on ownership beyond what's reasonably expected. /p h3Requirements /h3 ul li3+ years of experience in backend, infrastructure, or systems engineering /li liStrong proficiency in Go and Python /li liExperience building or operating a model serving platform or ML platform /li liSolid understanding of systems performance
- profiling, benchmarking, and optimising latency and throughput /li liFamiliarity with observability tooling (Prometheus, Grafana, OpenTelemetry, or similar) /li liUnderstanding of security fundamentals
- network isolation, authentication, encryption, multi-tenancy /li /ul h3Nice to have /h3 ul liExperience with NVIDIA Dynamo or similar inference orchestration/routing frameworks /li liHands‑on experience with GPU serving infrastructure (vLLM, Triton, TensorRT-LLM) /li liExperience with Kubernetes in a production environment (deployment, networking, resource management) /li liExperience operating at scale (10k+ RPS, multi-region, multi-cluster) /li liComfortable working on‑call or in incident response when things break /li /ul h3Why us? /h3 ul liOutstanding team: Work with some of the best engineers in the world, coming from hedge funds, big tech, AI startups and top universities. /li liOnce in a lifetime opportunity: Early‑stage company in the fastest-growing market in the world /li liOwnership: Shape how European AI companies access GPU compute /li liEuropean mission: Build sovereign, GDPR‑compliant AI infrastructure for the next generation of deep‑tech /li /ul h3About us /h3 pLyceum is building AI-native GPU infrastructure for the next generation of deep‑tech companies. We’re an early‑stage team moving fast, obsessed with customer value, and focused on building a category-defining product. /p /p