Generative AI Operations Engineer

We are seeking a highly motivated and experienced Generative AI Operations (GenAI Ops) Engineer to join our innovative team. In this role, you will be at the forefront of the AI revolution, responsible for building, deploying, and maintaining the operational infrastructure for our cutting-edge generative AI models and services. You will work closely with data scientists, machine learning engineers, and software developers to ensure our GenAI applications — especially complex, multi-agent systems — are scalable, reliable, and efficient across major cloud platforms. If you are passionate about operationalizing large-scale AI systems and want to make a significant impact, this is the role for you. This is a fully remote position that offers you the flexibility to work from any location in Armenia, whether it's your home or well-equipped offices in Yerevan or Gyumri. Responsibilities Build and Manage CI/CD Pipelines: Design, implement, and maintain robust, automated CI/CD pipelines for training, evaluating, and deploying large language models (LLMs) and AI agentsOrchestrate Agentic AI Workflows: Design, deploy, and manage sophisticated, multi-agent systems. Ensure seamless Agent-to-Agent (A2A) communication and collaboration between specialized agents to automate complex business processesManage Tool Integration: Implement and manage secure, scalable integrations between AI agents and external tools/APIs, leveraging open standards like the Model Context Protocol (MCP) to ensure interoperabilityLeverage AI-Powered Development: Utilize AI-powered development tools to accelerate the entire software development lifecycle, from writing infrastructure code and tests to troubleshooting operational issues in cloud environmentsInfrastructure as Code (IaC): Utilize cloud-native IaC services or cloud-agnostic tools like Terraform to define and manage the infrastructure required for GenAI workloadsModel Monitoring and Observability: Implement comprehensive monitoring and logging solutions to track model and agent performance, resource utilization, and system health. For agentic systems, this includes tracing the agent's actions and logging the multi-step conversational flowScalability and Performance Optimization: Design and implement scalable architectures for model serving and inference. Continuously optimize the performance and cost-effectiveness of our GenAI servicesSecurity and Compliance: Implement and enforce security best practices for our GenAI infrastructure and data. Ensure compliance with industry standards and regulations Requirements 3+ years in a DevOps, SRE, or MLOps role with a focus on cloud infrastructure and a background in cloud services (AWS, GCP, Azure)Skills in building and managing CI/CD pipelines (Jenkins, GitLab CI, or cloud-native services) and proficiency in at least one scripting language (e.g., Python, Bash)Familiarity with IaC tools (e.g., AWS CDK, CloudFormation, Terraform) and containerization/orchestration (Docker, Kubernetes)Track record of deploying and operating LLM inference (e.g., vLLM, Triton, TGI, Ray Serve, KServe/Seldon)Hands-on experience with LLM/app tracing and metrics (e.g., OpenTelemetry + Langfuse, Arize Phoenix, WhyLabs) and in building evaluation pipelines (offline/online, regression suites)Skills in operating retrieval pipelines: embedding generation, indexing/refresh strategies, vector DBs (Pinecone, Weaviate, Milvus, FAISS), and relevance monitoringExperience in running multi-agent workflows (LangGraph, CrewAI, AutoGen-like), including state management, retries, rate limits, tool-failure handling, and step-level auditingExperience in implementing guardrails: secrets isolation, tool/API permissions, prompt-injection defenses, data leakage prevention, PII redaction, and policy enforcementBackground integrating agents with external tools using MCP (or similar tool-calling standards) and operating tool registries is a plusFluent in English (B2+ level) Nice to have Master's degree or PhD in Computer Science, AI, Machine Learning, or a related fieldExperience with cloud-native GenAI services like AWS Bedrock, Azure AI Foundry, or Google Vertex AIFamiliarity with the architecture and operational challenges of Large Language Models (LLMs)Experience designing or managing multi-agent systems or complex, orchestrated workflowsKnowledge of monitoring and observability tools like Prometheus, Grafana, or DatadogRelevant cloud or DevOps certificationsStrong problem-solving skills and the ability to work effectively in a fast-paced, collaborative environment We offer We connect like-minded peopleDelivering innovative solutions to industry leaders, making a global impactEnjoyable working environment, whether it is the vibrant office or the comfort of your homeOpportunity to work abroad for up to two months per yearRelocation opportunities within our offices in 55+ countriesCorporate and social eventsWe invest in your growthLeadership development, career advising, soft skills and well-being programsCertifications, including GCP, Azure and AWSUnlimited access to EPAM's internal learning databaseFree English classes with certified teachersWe cover it allParticipation in the Employee Stock Purchase PlanMonetary bonuses for engaging in the referral programComprehensive medical & family care packageFour trust days per year for personal needsDiscounts for fitness clubsBenefits package (hotels, restaurants, stores and services) EPAM Armenia is a team of talented innovators united by a passion for technology. In 2014, we opened our first office in Yerevan, and now we have a second engineering hub in Gyumri. We've built a continuously learning organization that helps its employees rapidly advance their careers. Here you will work with the world's industry leaders, support impactful projects using the latest technologies, collaborate with multi-national teams, and have access to a wide variety of development opportunities.