MLOps Engineer

Andersen·Алматы·6 дн назад

MLOps Engineer

🏢 ОфисSeniorПолная занятость

Зарплата не указана

Вилки нет, про деньги придётся договариваться с нуля.

Нажмите на сигнал, чтобы увидеть, на чём он основан

Чем предстоит заниматься

Designing and owning the end-to-end MLOps architecture for production Machine Learning and Generative AI systems

Building and maintaining ML training, validation, deployment, serving, monitoring, and retraining pipelines

Defining and implementing the model promotion lifecycle across development, staging, and production environments

Building and maintaining model registry, experiment tracking, dataset/model versioning, and reproducible ML workflows

Designing scalable training and inference infrastructure, including GPU-backed workloads

Building and maintaining CI/CD pipelines for ML and AI workloads with automated testing, quality gates, approval controls, and rollback mechanisms

Implementing progressive delivery approaches for ML models, including shadow testing, canary releases, and blue-green deployments

Collaborating closely with Platform Engineering to run AI workloads on shared Kubernetes infrastructure

Translating ML infrastructure requirements into technical requirements for platform, security, capacity, and architecture teams

Establishing reusable MLOps project templates, shared pipeline components, and engineering standards

Implementing automated ML testing, including data validation, model regression tests, training-serving consistency checks, and evaluation gates

Owning production reliability of ML systems, including availability, latency, throughput, scalability, and operational stability

Building observability across infrastructure, data quality, model performance, and business impact

Configuring monitoring, alerting, incident response, runbooks, rollback procedures, and post-incident reviews for AI systems

Implementing automated model retraining based on schedules, events, and data/model drift

Managing the full model lifecycle, including deployment, monitoring, retraining, version promotion, and retirement

Tracking and optimizing infrastructure, training, inference, and GPU-related costs

Building and operating the production layer for Generative AI and LLM-based applications

Implementing LLM model gateways, routing, prompt management, prompt versioning, caching, and rate limiting

Implementing LLM guardrails, groundedness monitoring, sensitive-data protection, and prompt-injection mitigation

Building observability and permission controls for agentic AI systems

Implementing token-level and request-level consumption metering across Generative AI applications

Building cost attribution mechanisms by business unit, use case, application, model, tenant, and environment

Optimizing LLM workloads through model routing, prompt/context optimization, caching, batching, and selection of cost-efficient models

Applying hands-on Generative AI engineering practices, including prompt engineering, structured outputs, context management, embeddings, tool/function calling, and model adaptation where required

Evaluating emerging ML and Generative AI tools, models, and platforms and recommend technologies for adoption

Making and documenting architectural and build-vs-configure decisions for new AI capabilities

Producing architecture decision records, reference designs, technical documentation, and operational guidelines

Participating in architecture, capacity planning, technical roadmap, and platform strategy discussions

Performing code reviews, technical mentoring, pairing, and knowledge sharing to improve engineering standards across the team

Strong engineering experience across Software Engineering, DevOps/SRE, and MLOps for 5+ years

Production ownership of machine learning systems: you have operated, supported, and been accountable for ML in production

Deep hands-on experience with Docker and Kubernetes, including resource management and GPU workloads

Strong proficiency with GitLab CI, GitHub Actions, ArgoCD, or equivalent, including pipeline-enforced quality gates

Extensive experience with MLflow, Kubeflow, Feast, BentoML, KServe, SageMaker, Vertex AI, Databricks, or comparable platforms

Python at production engineering standard (typed, tested, packaged, and reviewed)

Infrastructure as Code (Terraform, Ansible, or equivalent, with real module and state management experience)

Production service engineering (stateless, configuration-driven services with structured logging, published API contracts, and centrally managed secrets)

Data services in production (PostgreSQL, caching, and message-driven asynchronous Processing)

Monitoring and observability (metrics, logging, error tracking, and ML-aware monitoring such as Evidently, WhyLabs, or Arize)

Proven collaboration with platform or infrastructure engineering teams, building on shared infrastructure rather than around it

Hands-on LLMOps experience: model gateways, prompt versioning, RAG pipelines, vector databases, evaluation harnesses, and guardrail frameworks

Generative AI consumption management: token metering, cost attribution across multiple applications or tenants, budget and quota controls, and demonstrable cost optimization of LLM workloads

Model evaluation and selection: building evaluation suites that objectively compare models on quality, latency, cost, and safety for a given task, and using them to drive adoption decisions

Practical generative AI engineering: prompt and structured output design, context management, embedding selection, tool calling, and fine-tuning or model adaptation

Experience operating agentic AI systems in production

Experience establishing an ML platform capability from an early stage

Cost engineering for AI workloads: GPU efficiency, inference optimization, and consumption attribution

Familiarity with AI governance and regulated environments — model risk management, auditability, and fairness testing

Experience with data quality frameworks and workflow orchestration

Level of English – Upper-Intermediate and above

Experience in teamwork with leaders in FinTech, Healthcare, Retail, Telecom, and others. Andersen cooperates with such businesses as Samsung, Siemens, Johnson & Johnson, BNP Paribas, Ryanair, Mercedes, TUI, Verivox, Allianz, T-Systems, etc

The opportunity to change the project and/or develop expertise in an interesting business domain

Job conditions – you can work both fully remotely and from the office or can choose a hybrid variant

Guarantee of professional, financial, and career growth! The company has introduced systems of mentoring and adaptation for each new employee

The opportunity to earn up to an additional 1,000 EUR per month, depending on the level of expertise, which will be included in the annual bonus, by participating in the company's activities

Access to the corporate training portal, where the entire knowledge base of the company is collected and which is constantly updated

Bright corporate life (parties / pizza days / PlayStation / fruits / coffee / snacks / movies)

Certification compensation (AWS, PMP, etc)

Referral program

Private health insurance and sports compensation, depending on the type of employment

Дополнительно

Andersen is hiring an MLOps Engineer for a project delivering scalable digital solutions and supporting reliable AI and technology platforms across diverse organizations

The customer is a government-backed organization focused on socio-economic development through digital and business solutions. They aim to improve labor markets, enhance employment opportunities, and support public and private sector growth. Their services include digital platforms, automation, and training programs to develop human capital

The project is focused on delivering digital and technology solutions for government, semi-government, and private-sector organizations. It supports diverse business needs through the development and implementation of reliable, scalable, and efficient solutions