DevOps Engineer - AI Infrastructure & Orchestration

ITLT • Polish: C1 • Python • 4 months ago
Apply now
Save
368,611open jobs
9,439companies
50,719added this week
Browse all
Location
In office
Employment
Full-Time
Overview
Company
Impact
Profile match

ITLT

ITLT is a Polish IT services, body leasing, and talent acquisition firm based in Warsaw, Poland. Founded in 2015 as part of the broader LeasingTeam Group (one of Poland's largest HR consulting ecosystems), the company specializes in IT outsourcing and recruitment solutions across Europe.
itlt.pl • HQ: Warsaw, Poland • Human Resources • Information Technology • IT Outsourcing

W ITLT pomagamy naszym zaprzyjaźnionym firmom przekształcać ambitne pomysły w cyfrową rzeczywistość.

Z nastawieniem na wyzwania, ciekawość technologii i zwinność - współtworzymy wyjątkowe rozwiązania IT.

Aktualnie poszukujemy osób na stanowisko: DevOps Engineer (AI Infrastructure & Orchestration)

Responsibilities

  • Deployment i utrzymanie vLLM na Openshift Kubernetes (bare-metal GPU)
  • Orkiestracja i optymalizacja GPU (NVIDIA)
  • Automatyzacja lifecycle modeli (HF/S3: pull, versioning, hot-swap)
  • HPA (queue depth, GPU memory)
  • Tuning vLLM (performance, batching, memory)
  • Metryki inference (tokeny, latency, errors) + tracking zużycia per user/API key
  • Grafana dashboards (GPU, TTFT, RPS, koszty, quota)
  • Alerting (GPU failures, latency, anomalies)
  • API Gateway (NGINX: auth, rate limit, routing)
  • Security + isolation + audit logging
  • Monitoring stack (Prometheus, Grafana, ELK, OpenTelemetry)
  • Automatyzacja (Python/Bash/Go)
  • CI/CD (GitLab CI, Jenkins, ArgoCD)
  • SLA 99.9%, >70% GPU utilization, MTTR reduction

Requirements

  • Stawka: 190 PLN/h na FV
  • Miejsce pracy/praca zdalna: Praca zdalna (Remote)
  • Wymiar pracy: Fulltime
  • Sektor: AI/Telco
  • Projekt: On-prem LLM platform - orkiestracja i monitoring vLLM na GPU clusterze
  • Zespół: 6-8os.
  • Proces rekrutacji: 1-etapowy (spotkanie zdalne via MS Teams). Sporadycznie możliwe dodatkowe krótkie spotkanie - połączone z decyzją
  • Szacowany czas trwania projektu: Długoterminowy/Bezterminowy
  • Czas pracy/Strefa czasowa: Standardowe polskie godziny pracy
  • Technologie na projekcie: Kubernetes (OpenShift), vLLM, NVIDIA GPU (H100/H200/B300), Prometheus, Grafana, ELK, OpenTelemetry, Python, Bash, Go, GitLab CI, Jenkins, ArgoCD, bare metal

Benefits

  • Min. 5+ lat doświadczenia w DevOps/SRE
  • Min. 2 lata doświadczenia w MLOps lub AI Infrastructure
  • Doświadczenie w deploymencie vLLM w środowisku produkcyjnym
  • Znajomość PagedAttention i continuous batching (vLLM)
  • Bardzo dobra znajomość Kubernetes i Openshift
  • Doświadczenie w infrastrukturze GPU NVIDIA (CUDA drivers, container toolkit, debugging)
  • Umiejętność zarządzania i debugowania środowisk GPU
  • Doświadczenie w budowie systemów observability od zera
  • Umiejętność tworzenia custom Prometheus exporters
  • Bardzo dobra znajomość Python (automation, tooling)
  • Znajomość Bash i Go
  • Doświadczenie w pracy z CI/CD (GitLab CI, Jenkins, ArgoCD)
  • Doświadczenie w środowiskach on-prem / bare-metal

Nice to have:

  • Znajomość GPU orchestration w Kubernetes (device plugins NVIDIA)
  • Znajomość model quantization (AWQ, GPTQ)
  • Znajomość FinOps dla AI infrastructure
  • Znajomość vector databases (Milvus, Qdrant)
Free account
Stop reading job ads. Get the ones that fit.
One free account turns this page into a shortlist built around your stack, your level and your pay.
Match on every job. Stack, seniority, pay and location, scored against your profile.
368,611 open roles. Read straight off company career pages, refreshed every day.
Unlimited applications. Every one you send is tracked in one place, on-site or on a company board.
3 tailored CVs a month. Rewritten for the exact job you are applying to. Included free.
Create a free account
Free forever. No card. Under a minute.

Your match

How well do you fit this role?
Two answers are enough for a real match. No account needed.
Check my fit
Answers stay in this browser until you create an account.

Recommended for you based on this role

Similar stack
Same company
In your city
$220k – $325k per year • Remote/Hybrid • Full-Time • 15+ years exp • New York
DevOps
AWS
Azure
CI/CD
GCP
Kubernetes
Platform Engineering
Cybersecurity
Threat Modeling
Apply
≈ $140k – $253k per year (Estimated) • In office • 5+ years exp • Long Beach
C++
Rust
C++
Protobuf
AI/ML
Human-in-the-Loop
DevOps
CI/CD
Vector
Apply
≈ $21k – $57k per year (Estimated) • Remote/Hybrid • Full-Time • 6+ years exp • Bachelor's Degree • Noida
C#
SQL
TypeScript
JavaScript
C#
.NET
Frontend
Angular
DevOps
Azure
Azure DevOps
CI/CD
Git
TeamCity
Apply
≈ $16k – $42k per year (Estimated) • Remote/Hybrid • Full-Time • 3+ years exp • Bachelor's Degree • Noida
C#
SQL
TypeScript
JavaScript
C#
.NET
Frontend
Angular
DevOps
Azure
Azure DevOps
CI/CD
Git
TeamCity
Apply
≈ $21k – $57k per year (Estimated) • Remote/Hybrid • Full-Time • 8+ years exp • Bachelor's Degree • Noida
C#
SQL
TypeScript
JavaScript
C#
.NET
Frontend
Angular
DevOps
Azure
Azure DevOps
CI/CD
Git
TeamCity
Apply
Manual QA Engineer 3 days ago
$26k – $38k per year (net) • In office • Contractor
C#
JavaScript
Python
SQL
DevOps
CI/CD
Management
Jira
QA
Cypress
Playwright
Selenium
TestRail
Apply
Remote/Hybrid • Full-Time
AI/ML
LiteLLM
LLM
DevOps
AWS
Azure
Docker
GitOps
Helm
Kubernetes
Platform Engineering
Terraform
Vector
IAM
Apply
$76k – $78k per year • In office • Full-Time
Elixir
SQL
DevOps
Git
Apply
SAP Experts 5 days ago
$64k – $86k per year (net) • In office • Contractor
ABAP
ABAP
CDS Views
SAP Fiori
Apply
$70k – $86k per year (net) • In office • Contractor
Java
Java
Spring Boot
Databases
Apache Kafka
Apply
See all jobs
This is one of many
368,611 more open roles from verified company boards, updated every day.
Browse all jobs Get matched roles