DevOps Engineer (вакансія неактивна)

We’re building AI-driven SaaS platforms that power intelligent automation for SMBs using LLMs, AI agents, and data-intensive pipelines.

You’ll work in startup mode, helping scale AI systems from early R&D to secure, fault-tolerant production infrastructure.

Your Role

You will own the cloud infrastructure, deployment pipelines, and reliability of AI-powered systems.

Your mission is to ensure scalability, security, and cost-efficient operation of AI workloads in production.

You’ll work closely with backend and AI engineers to turn experimental AI features into robust, observable, and resilient systems.

YOUR STACK:

• Design and build Python backend services for AI-driven products- Build async, scalable APIs for AI inference and orchestration- Move AI prototypes into production-grade systems.
• Ensure observability, performance, and cost efficiency of AI workloads.
• Design data pipelines for embeddings, vector search, and context retrieval.
• Implement LLM-powered features (agents, tools, workflows, RAG).

Cloud & Infrastructure

• AWS (VPC, EC2, ECS/EKS, RDS, S3, IAM, CloudWatch)-
• Auto-scaling, load balancing, multi-AZ setups
• Terraform (IaC, modules, environments)

CI/CD & Runtime

• Docker
• CI/CD pipelines (GitHub Actions / GitLab CI / similar)
• Blue/green & rolling deployments

Security

• IAM, least-privilege access
• Secrets management
• Network security (VPC, security groups, private subnets)
• Compliance-aware setups (SOC2 / basic security best practices)

Reliability & Observability

• Monitoring, logging, tracing
• SLOs, alerting, failure detection
• Backup & disaster recovery strategies

AI & Data Considerations

• Supporting LLM inference workloads (latency, throughput, cost)
• GPU / high-CPU workloads (nice to have)
• Caching and batching strategies for AI APIs
• Safe rollout of AI features with controlled blast radius

NICE-TO-HAVE:

• Experience with high-load or data-intensive SaaS systems
• Knowledge of AI infrastructure patterns (model serving, vector DB hosting)
• Security audits or compliance exposure
• Cost optimization for AI & data pipelines
• Kubernetes (EKS) production experience

RESPONSIBILITIES:

• Design and maintain AWS infrastructure for AI-driven SaaS platforms- Build secure, scalable, fault-tolerant environments- Ensure high availability, disaster recovery, and smooth scaling- Optimize cloud cost for AI-heavy workloads
• Own observability, alerting, and incident response
• Design deployment strategies for AI services and inference workloads
• Implement infrastructure as code using Terraform

OFFER:

• Remote work;
• Open management without bureaucracy;
• Salary reviews according to the results of performance appraisal;
• 10 days paid sick leave and 18 working days’ vacation;
• Days off on National/Bank Holidays according to the legislation of Ukraine;
• Real AI in production — not just demos;
• Strong R&D culture with ownership;
• Opportunity to shape AI backend architecture from day one;
• Flexible remote work;
• Direct impact & fast feedback loops.