17 Nov
|
Clevanoo
|
India
DevOps Engineer I – AWS
Pune, Fulltime, Hybrid
Key Responsibilities
Own and maintain production AWS infrastructure with high availability, fault tolerance, and proactive monitoring
Build and manage scalable cloud infrastructure using Terraform and Ansible on AWS
Deploy and manage AI/LLM workloads, vector databases, and model inference pipelines
Design and maintain secure CI/CD pipelines for microservices and AI/ML systems
Implement security best practices including IAM policies, secrets management, and vulnerability scanning
Set up observability and monitoring for both system and AI metrics (latency, throughput, cost, usage
) • Optimize cloud costs, particularly for GPU-backed and compute-intensive AI workloads
Manage VPC networking, DNS, load balancing, and secure connectivity across AWS environments
Collaborate closely with AI/ML engineers and product teams to ensure infrastructure supports fast experimentation and reliable deployment
Required Qualifications
3 - 5 years of hands-on experience in DevOps, SRE, or cloud infrastructure roles
Proven experience working at a product-based company with quick-paced engineering teams
Strong hands-on expertise with core AWS services: EKS, ECS/Fargate, EC2, S3, RDS, SageMaker, Lambda, VPC, and CloudFront
Experience deploying and managing AI/LLM workloads, vector databases (e.g., Pinecone, Weaviate, pgvector), and LLM APIs (OpenAI, Bedrock, etc.)
Solid expertise in Docker, Kubernetes (EKS), Terraform, and Ansible
Proficiency in Python scripting for automation, tooling, and infrastructure workflows — this is a mandatory requirement
Robust understanding of Linux/Unix systems, preferably Ubuntu
Sound knowledge of networking fundamentals, security architecture, and IAM principles on AWS • Demonstrated experience delivering AI projects in production — not just experimental or PoC environments
Preferred Skills
Experience with LLMOps practices — prompt versioning, model monitoring, RAG pipelines, and inference optimization
Familiarity with AI/ML frameworks (SageMaker Pipelines, MLflow, Kubeflow) and model serving patterns
Hands-on experience with observability tools such as Prometheus, Grafana, CloudWatch, or OpenTelemetry
Automation-first mindset with the ability to work across complex distributed systems
Exposure to AWS Bedrock, Rekognition, Comprehend, or other managed AI/ML services
Solid debugging, performance tuning, and root cause analysis skills
📌 Devops Engineer I – Aws Pune (India)
🏢 Clevanoo
📍 India