Data engineer moving into LLM and AI engineering. I help teams build production AI systems on top of solid data foundations: RAG pipelines, evals, and LLMOps.https://balvindersingh.com/en-cahttps://balvindersingh.com/writing/evals-are-unit-tests/https://balvindersingh.com/writing/evals-are-unit-tests/If a prompt change can silently regress your product, you do not have an engineering process - you have a demo. A practical starting point for LLM evaluation suites.Wed, 11 Nov 2026 00:00:00 GMTevalsLLMOpshttps://balvindersingh.com/writing/llm-projects-fail-on-the-data-layer/https://balvindersingh.com/writing/llm-projects-fail-on-the-data-layer/Teams debug prompts when they should be auditing retrieval. The failure mode I see most in stalled LLM projects is a data problem wearing a model costume.Wed, 11 Nov 2026 00:00:00 GMTLLM engineeringdata quality