Dear recruiters, if you are looking for: - AWS, Azure, GCP - Bedrock, Vertex AI, Azure OpenAI - LangChain, LangGraph, Strands agents - Kubernetes, Docker, Backstage - Terraform, CloudFormation, Pulumi - Jenkins, GitHub Actions, Azure DevOps - Python, Java, FastAPI, Spring Boot - SonarQube, Checkmarx, OWASP ZAP, and 20 DevSecOps tools - OpenTelemetry, Prometheus, Grafana, Loki, ELK - GPU workloads, RAG, AI agents, vector databases, MCP, Evals - SLI, SLO, Error Budget, OnCall - Production support, disaster recovery, cost optimization, cybersecurity That's not a DevOps Engineer. That's the DevOps team for 5 different companies.

Your model was trained on 2025 data. How do you make it aware of 2026? Most people answer: "Retrain it." That's usually the wrong answer. The model has a knowledge cutoff. A model's weights encode patterns learned from its training data. Once training is complete, those weights don't automatically change when new information becomes available. So, how do you give it new knowledge? You don't update its memory. You give it fresh information when it needs to answer a question. There are several ways to do this, but each comes with trade-offs. 1. Web search and tool calls > The model fetches live information before answering. > Trade-off: Always fresh, but slower, and only as good as the sources it finds. 2. RAG (Retrieval-Augmented Generation) > Store your documents in a vector database, retrieve the relevant pieces, and add them to the prompt for each query. > Trade-off: Great for private data, but you now own a retrieval pipeline. Bad chunking leads to bad answers, and if you don't re-embed updated documents, your index becomes stale. 3. Long context > Pass the whole document directly into the prompt. > Trade-off: Simple, but cost grows with every token, and too much irrelevant text can distract the model. 4. MCP connectors > Give the model governed access to private systems like Gmail, Drive, Slack, or your databases. > Trade-off: Powerful, but permissions, security, and access control need careful design. 5. Memory > Store facts from past conversations and inject them when relevant. It's retrieval, just scoped to the user or agent. > Trade-off: Makes the system feel current and personal, but stored facts can go out of date or be wrong. 6. Fine-tuning > Further train an existing model on your own data. > Trade-off: Great for style and behavior, but poor at reliably injecting facts. It can leave the model confidently wrong, and when your facts change, you're paying to train again. My take: RAG and tool calling for knowledge. Fine-tuning for behavior. You don't need to give the model everything. You need to give it the right information at the right time