https://ashimsharma10.github.io/blog Software engineer sharing projects, notes, and guides on ML infrastructure. en-us sharmaashim00@gmail.com (Ashim Sharma) sharmaashim00@gmail.com (Ashim Sharma) Mon, 07 Sep 2026 00:00:00 GMT https://ashimsharma10.github.io/blog/world-models https://ashimsharma10.github.io/blog/world-models A world model is a learned simulator. Give it a state and an action and it predicts what happens next. This write-up follows the idea from Ha and Schmidhuber's V+M+C agent through Dreamer, MuZero and TD-MPC, to Genie, Cosmos and V-JEPA, the drift that comes with imagining too far ahead, LeCun's case for predicting representations instead of pixels, and why robots need all of this. Mon, 07 Sep 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) world-modelsreinforcement-learningroboticsphysical-aijepamodel-based-rl https://ashimsharma10.github.io/blog/rlvr-and-the-experience-era https://ashimsharma10.github.io/blog/rlvr-and-the-experience-era Post-training has moved from imitating human labels to learning from verifiable outcomes. This write-up covers the RLVR objective, GRPO and the choice of KL penalty, advantage collapse and the methods that recover the lost gradient, reward hacking and noisy verifiers, outcome versus process reward models, the production data flywheel that turns failures into weight updates, long chain-of-thought and latent reasoning, and the OpenRLHF stack that runs it all. Sun, 06 Sep 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) rlvrreinforcement-learninggrpollmcontinual-learningreasoning https://ashimsharma10.github.io/blog/architecture-of-memory-kv-cache https://ashimsharma10.github.io/blog/architecture-of-memory-kv-cache Modern LLM inference is memory-bound, and the KV cache is the reason. This report walks through why the cache exists, how large it gets, the attention changes that shrink it (GQA, DeepSeek MLA), how engines like vLLM and SGLang manage it, how quantization and eviction compress it, and how disaggregated serving moves it between machines. Sat, 05 Sep 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) kv-cachellminferenceattentiongpu https://ashimsharma10.github.io/blog/mixture-of-experts https://ashimsharma10.github.io/blog/mixture-of-experts Sixteen questions about sparse models, each one the thing you would ask after hearing the last answer: what the router really is, why experts do not learn topics, why sparsity stops paying once you batch, and what it costs to serve one. Mon, 17 Aug 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) moellmarchitectureinferencetraining https://ashimsharma10.github.io/blog/system-design-etl-pipelines https://ashimsharma10.github.io/blog/system-design-etl-pipelines How I would design the pipeline that moves a legacy database onto Azure: bulk load and CDC, a medallion lakehouse with a quality gate that actually stops things, star schemas and SCD2, a feature store, and the security, monitoring and cutover plan around it. Mon, 17 Aug 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) data-engineeringazuresystem-designinfrastructuremlops https://ashimsharma10.github.io/blog/evaluation-engineering https://ashimsharma10.github.io/blog/evaluation-engineering How to tell whether an LLM system works, and how to keep it working: test cases, graders, judges, groundedness, CI gates, live signals, traces, latency, schemas, injection defense, and PII masking. Thu, 13 Aug 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) evalsobservabilityguardrailsllmagents https://ashimsharma10.github.io/blog/self-improving-agents https://ashimsharma10.github.io/blog/self-improving-agents An agent that gets better on its own has to change something about itself, and something has to check the change. This post walks the six things it can change, the checker that decides whether any of it worked, the ceiling it runs into, the ways it breaks, and the loop teams actually run in production. Thu, 13 Aug 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) agentsaillmself-improving-agentscontinual-learningloop-engineering https://ashimsharma10.github.io/blog/vllm-how-a-token-gets-served https://ashimsharma10.github.io/blog/vllm-how-a-token-gets-served What happens inside a serving engine: why the GPU fills up with something other than the model, what paging the cache buys you, why reading a prompt and writing an answer fight each other, and which knobs settle the fight. Thu, 13 Aug 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) vllmllminferencegpukv-cache https://ashimsharma10.github.io/blog/data-science-fundamentals https://ashimsharma10.github.io/blog/data-science-fundamentals What a senior data scientist must know cold: statistics, experiment design, causal inference, metric craft, modeling judgment, and evaluation, plus one section on the 2026 market and one on interview prep. Tue, 11 Aug 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) data-sciencestatisticsmachine-learningcausal-inferenceexperimentation https://ashimsharma10.github.io/blog/ai-engineers-swiss-knife https://ashimsharma10.github.io/blog/ai-engineers-swiss-knife Forty production questions on agentic systems, answered plainly: evals, guardrails, quality measurement, observability, security, and token economics. Sun, 02 Aug 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) llmagentsevalsguardrailsguide https://ashimsharma10.github.io/blog/graph-engineering-for-agentic-ai https://ashimsharma10.github.io/blog/graph-engineering-for-agentic-ai What graph engineering is, how it differs from loops and workflow engines, when to build one, a refund approval worked through end to end, and the failure modes to watch for. Tue, 28 Jul 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) agentsaillmgraph-engineeringmulti-agent https://ashimsharma10.github.io/blog/quantum-and-particle-physics https://ashimsharma10.github.io/blog/quantum-and-particle-physics A plain-language tour of quantum physics a century after it was born: from photons and superposition to the 17 particles behind everything and the quantum tech in your pocket. With interactive demos. Thu, 23 Jul 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) physicsquantum-mechanicsparticle-physicsstandard-model https://ashimsharma10.github.io/blog/from-prompting-to-loops https://ashimsharma10.github.io/blog/from-prompting-to-loops Why AI work moved from single prompts to loops, the main types of loops, and examples of goal-driven loops in practice. Mon, 20 Jul 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) agentsllmloop-engineeringai https://ashimsharma10.github.io/blog/claude-code-skills-subagents-and-hooks https://ashimsharma10.github.io/blog/claude-code-skills-subagents-and-hooks Build your own Claude Code extensions from scratch: skills with SKILL.md, custom subagents, and lifecycle hooks. Copy-paste examples, a combined worked workflow, and a tour of the most popular skill repos on GitHub. Wed, 08 Jul 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) claude-codeagentsskillssubagentshooksai https://ashimsharma10.github.io/blog/riemann-zeta-and-the-riemann-hypothesis https://ashimsharma10.github.io/blog/riemann-zeta-and-the-riemann-hypothesis Why the zeros of the zeta function govern the primes, built from scratch with live graphs you can zoom, drag, and animate. Wed, 08 Jul 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) mathematicsnumber-theoryriemann-hypothesisprimes https://ashimsharma10.github.io/blog/mlops-tooling-from-experiment-tracking-to-production https://ashimsharma10.github.io/blog/mlops-tooling-from-experiment-tracking-to-production A conceptual guide to MLOps tooling — MLflow, artifact versioning, reproducible pipelines, framework integrations, alternatives, and deploying and improving models in production. Fri, 03 Jul 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) mlopspythondeep-learningpytorchinfrastructureguide https://ashimsharma10.github.io/blog/cpu-gpu-tpu-hardware-deep-dive https://ashimsharma10.github.io/blog/cpu-gpu-tpu-hardware-deep-dive Why the same matrix multiply runs 100× faster on one chip than another. CPU/GPU/TPU internals, tensor cores, precision, GPU memory and the roofline, interconnects, and when to use each. Visual-first. Mon, 22 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) gputpuhardwareml-systemscuda https://ashimsharma10.github.io/blog/linux-systems-handbook https://ashimsharma10.github.io/blog/linux-systems-handbook Hands-on handbook covering the Linux filesystem, shell, processes, storage, networking, and system hardening — built around the core models behind every production problem. Sun, 21 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) linuxsystemskernelnetworking https://ashimsharma10.github.io/blog/harness-context-loop-engineering https://ashimsharma10.github.io/blog/harness-context-loop-engineering A practical field guide to the systems that wrap an LLM and turn it into a reliable agent — with patterns, worked examples, real deployments, and where the field is heading (mid-2026). Sat, 13 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) agentsllmharness-engineeringloop-engineeringcontext-engineeringai https://ashimsharma10.github.io/blog/docker-fundamentals https://ashimsharma10.github.io/blog/docker-fundamentals Docker from first principles — runtime stack, OverlayFS, bridge networking, security, and kernel internals. Thu, 11 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) dockercontainersdevopsinfrastructurenetworking https://ashimsharma10.github.io/blog/anyscale-ray-deep-dive https://ashimsharma10.github.io/blog/anyscale-ray-deep-dive A comprehensive technical writeup covering why distributed computing for AI is hard, what Ray is, what Anyscale adds on top of it, how it compares to the alternatives, and how to actually use it. Wed, 10 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) rayanyscaledistributed-computingdeep-learninginfrastructure https://ashimsharma10.github.io/blog/from-raw-data-to-ml-ready-a-pandas-walkthrough https://ashimsharma10.github.io/blog/from-raw-data-to-ml-ready-a-pandas-walkthrough Full ML data prep lifecycle in Pandas: load, clean, impute, engineer features, encode, scale, and ship to model. Tue, 09 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) pandasdata-sciencefeature-engineeringpythonguide https://ashimsharma10.github.io/blog/ml-engineer-comprehensive-technical-prep-guide https://ashimsharma10.github.io/blog/ml-engineer-comprehensive-technical-prep-guide ML engineer prep: Python infra, NumPy, PyTorch, distributed training, scientific formats, MLflow, and common coding patterns. Sun, 07 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) pythonpytorchnumpydistributed-trainingmlopsguide https://ashimsharma10.github.io/blog/pytorch-from-first-tensor-to-distributed-training https://ashimsharma10.github.io/blog/pytorch-from-first-tensor-to-distributed-training Deep guide for ML engineers: tensors, autograd, nn.Module, training loops, DDP, FSDP, checkpointing, and debugging at scale. Sun, 07 Jun 2026 00:00:00 GMT sharmaashim00@gmail.com (Ashim Sharma) pytorchdeep-learningdistributed-trainingguide