We share everything we learn — real use cases, real production lessons. Technical deep-dives on MLOps, model deployment, AI reliability, and more.
📝 Building in public
Posts authored by the Resilio Tech Team. More in-depth tutorials and case studies coming soon.
A practical guide to AI observability for production systems — including latency, drift, token usage, retrieval quality, and the dashboards teams actually use during incidents.
A hands-on guide to building production MLOps pipelines on Kubernetes — covering CI/CD for models, automated retraining, model registry integration, and deployment strategies.
How to design an LLM gateway for production use cases, including multi-model routing, guardrails, quotas, usage logging, and cost-aware fallbacks.
A practical guide to batching LLM inference workloads, including static batching, dynamic batching, queue controls, and when higher throughput starts hurting latency.
Why prompts need versioning, change control, and rollback paths just like code and model releases, especially when LLM behavior changes under real traffic.
A pragmatic guide to internal ML platforms on Kubernetes, covering the patterns that reduce platform sprawl and the abstractions teams actually use in production.
How to use Terraform to provision AI infrastructure safely, with practical guidance on GPU node pools, registries, pipeline dependencies, and avoiding drift across environments.
How to build CI/CD for ML systems with data validation, schema checks, shadow evaluations, and deployment gates that go beyond ordinary application unit tests.
How to evaluate LLM output variants when the response is free-form text, using pairwise comparison, rubric scoring, human review, and practical experimental design.
How to build an evaluation pipeline for ML and LLM systems that continuously catches regressions in quality, policy behavior, cost, and runtime health before they hit production users.
3/30/2026 • 6 min read
3/29/2026 • 8 min read
3/28/2026 • 6 min read
3/27/2026 • 5 min read