Kyivstar

MLOps Engineer (LLM Infrastructure)

Job Description

About us:

Kyivstar.Tech is a Ukrainian hybrid IT company and a resident of Diia.City.
We are a subsidiary of Kyivstar, one of Ukraine's largest telecom operators.

Our mission is to change lives in Ukraine and around the world by creating technological solutions and products that unleash the potential of businesses and meet users' needs.

Over 500+ KS.Tech specialists work daily in various areas: mobile and web solutions, as well as design, development, support, and technical maintenance of high-performance systems and services.

We believe in innovations that truly bring quality changes and constantly challenge conventional approaches and solutions. Each of us is an adherent of entrepreneurial culture, which allows us never to stop, to evolve, and to create something new.


What you will do
  • Design and implement scalable ML infrastructure (cloud-native or on-premises) to support experimentation and production deployment of NLP/LLM models
  • Build end-to-end pipelines for model training, validation, and deployment, automating workflows from data ingestion to model evaluation
  • Collaborate with Data Scientists and ML Engineers to ensure infrastructure meets performance and latency requirements
  • Implement best practices in MLOps: automated testing, CI/CD for model updates, version control for code, data, and models
  • Set up monitoring and alerting for deployed models and pipelines, track performance and accuracy drift
  • Manage and optimize Kubernetes-based deployment environments, containerize ML services, and ensure system scalability
  • Maintain infrastructure-as-code for cloud resource provisioning (e.g., Terraform, Ansible)
  • Provide code reviews, troubleshoot across the ML lifecycle, and continuously improve system robustness


  • Qualifications and experience needed
  • 4+ years of experience in DevOps, MLOps, or ML Infrastructure roles
  • Strong foundation in software engineering and DevOps principles for machine learning
  • Extensive experience with cloud platforms (AWS, GCP, or Azure) and infrastructure-as-code tools (Terraform, CloudFormation)
  • Proficiency in Docker, Kubernetes, and orchestration tools (e.g., Helm)
  • Hands-on experience with CI/CD pipelines for ML (Jenkins, GitLab CI, GitHub Actions)
  • Strong coding skills in Python, with scripting experience (Bash, Go, Java, or C++)
  • Understanding of ML lifecycle, pipelines (Kubeflow, Airflow), and model serving frameworks (TensorFlow Serving, TorchServe, NVIDIA Triton)
  • Experience with monitoring tools (Prometheus, Grafana, CloudWatch) and model performance tracking
  • Knowledge of security best practices in ML deployments and compliance standards
  • Excellent collaboration skills and experience working in cross-functional teams


  • A plus would be
  • Experience deploying or fine-tuning large language models (LLMs) in production
  • Knowledge of model optimization techniques (model parallelism, quantization, DeepSpeed, Hugging Face Accelerate)
  • Experience with distributed computing frameworks (Ray, Spark) and streaming platforms (Kafka, Flink)
  • Familiarity with ML experiment tracking tools (MLflow, Weights & Biases, DVC)
  • Knowledge of vector databases (Pinecone, Weaviate, FAISS) for retrieval-augmented generation
  • Exposure to HPC environments or on-prem GPU clusters for large-scale training

  • What we offer
  • Office or remote – it’s up to you. You can work from anywhere, and we will arrange your workplace
  • Remote onboarding
  • Performance bonuses for everyone (annual or quarterly — depends on the role)
  • We train employees: with the opportunity to learn through the company’s library, internal resources, and programs from partners
  • Health and life insurance
  • Wellbeing program and corporate psychologist
  • Reimbursement of expenses for Kyivstar mobile communication