Hey, that’s me! Rahish · AI/ML Engineer I build & teach production AI
Hi, I’m Rahish · AI/ML Engineer
★ 4.9
Ship LLMs, RAG & Agents That Survive Production.
Move past fragile prompt demos. Learn how language models, hybrid retrieval, tool-calling agents, and evaluation harnesses actually work — through structured readable courses, runnable Python code, and daily frontier AI analysis.
- 4 structured readable tracks
- 34+ hands-on lessons
- 140+ daily AI engineering briefings
01 / Structured Curriculum
Four readable paths. Zero passive fluff.
Every course is built like a modern engineering handbook — sidebar curriculum, runnable code blocks, architecture diagrams, “Watch out” failure boxes, and progress tracking.
Python for AI Developers
Virtual environments, type hints, async HTTP calls, JSONL dataset pipelines, NumPy/Pandas essentials, and a complete data-prep project before your first model call.
LLM Fundamentals
Tokenization, next-token probabilities, system/developer/user roles, temperature & top-p sampling, structured JSON outputs, and latency/cost instrumentation.
Building RAG Systems
Document chunking trade-offs, dense embeddings, vector indexes, hybrid BM25 + vector search, cross-encoder reranking, score floors, and grounded citations.
Generative AI & Agents
Tool calling schemas, ReAct loops, state graphs, memory & context compaction, human-in-the-loop approvals, and automated evaluation suites for agents.
02 / The Production Gap
Every AI demo works on five tweets. Production breaks at 2:00 AM.
“Just wrap an LLM call and stuff top-5 chunks into the prompt.”
- 01Blindly splits PDFs every 500 characters — slicing tables and policy clauses in half.
- 02No similarity score floor — when retrieval misses, the model confidently invents a policy.
- 03Unbounded agent loops — one flaky tool call triggers 12 retries and burns $40 in tokens.
- 04Evaluated by “vibes” on 3 manual prompts instead of a repeatable golden dataset.
Deterministic guardrails around probabilistic models.
- 01Structure-aware chunking + hybrid BM25 & dense retrieval with cross-encoder reranking.
- 02Explicit score thresholds and abstention paths (
"I don't have enough context") with inline citations. - 03Strict tool schemas, step budgets, idempotency keys, and human-in-the-loop checkpoints.
- 04Automated faithfulness, recall@k, latency, and cost-per-task evaluation before every deploy.
03 / Built for Deep Focus
Read at your speed. Ship as you go.
No 40-minute rambling videos to scrub through when you need one code pattern. Every lesson combines clear intuition, copy-ready Python, and embedded video walkthroughs.
Code + Expected Output + Pitfalls
Every concept is paired with minimal runnable Python, real token/cost numbers, and “Watch out” callouts from production incidents.
AI System Design & JD Prep
Practice deep technical questions on RAG trade-offs, agent orchestration, MCP, and evaluation with company-specific tracks.
04 / The Path
The AI Developer Roadmap.
Eight stages from your first Python script to shipping production AI products. Start at stage one, or jump in wherever you are — each free course maps to a stage.
- 01FoundationsFree course →
- 02AI/ML BasicsComing soon
- 03GenAI & LLMsFree course →
- 04RAGFree course →
- 05AI AgentsFree course →
- 06Azure AI FoundryFree course →
- 07MLOpsComing soon
- 08AdvancedComing soon
05 / Daily AI Writing
Latest frontier model & systems dispatches.
OpenAI to Acquire Pierre for Codex Code Tools
OpenAI says it will acquire Pierre Computer, maker of Code Storage and the Trees and Diffs libraries used in Codex; closing needs regulatory approvals.
PFN Releases Open-Weight PLaMo 3 Translate Models
PFN released open-weight PLaMo 3 Translate in four sizes from 0.8B to 31B for offline use; commercial use is free with registration up to 1B yen revenue.
XPENG Details Open-Source GroundingPI Perception Model
GroundingPI, a 4B open-source perception model from XPENG-affiliated and academic researchers, outscored GPT-6 Astra across 34 benchmarks in the team’s tests.
Apple Opens Siri AI to All Developers in iOS 27.3 Beta
Apple’s Developer Preview in the iOS 27.3 betas lets any app bring content and actions into Siri AI via App Intents, plus new skills for complex requests.
Fal Raises $1.3B at $16B Valuation, Bloomberg Reports
Fal raised $1.3 billion in a Series F led by Bessemer at a $16 billion valuation, Bloomberg reported, as demand for its AI image and video inference grows.
OpenAI Teams With Mazda to Test AI on Vehicle Design
OpenAI started a research collaboration with Mazda’s aerodynamics and crash-safety engineers and shared how GPT-6 Astra helps design physical products.
Tencent Releases Hy4 With Vision and Computer Use
Tencent released Hy4, which adds vision and computer use for the first time, on Tencent Cloud and OpenRouter at the same API price as Hy4 preview.
Anthropic’s FlashProve Proves Which AI Model Answered
Anthropic open-sourced FlashProve, a research prototype that uses zero-knowledge proofs to show a reply came from a committed model without exposing weights.
IndiaAI Releases EKA-1 and Offline-Capable Dhīr AI Models
IndiaAI Mission released Soket’s EKA-1, a 26.3B-parameter model for 22 Indian languages, and ZenteiQ’s open-source Dhīr 2B and 5B for offline use.
Anthropic Discloses $895.4B in Compute Commitments
Anthropic’s amended IPO filing lists about $895.4 billion in compute and infrastructure commitments and $17.0 billion in revenue in the September quarter.
CrowdStrike Launches AI Kill Switch to Stop Rogue Agents
CrowdStrike's Falcon Guardian AI Kill Switch can terminate a rogue agent first at the Gateway (endpoint soon), block relaunch, and cut network access.
Tutor Intelligence Raises $75M to Scale Robot Workers
Tutor Intelligence raised a $75M Series B led by a16z, bringing funding to $117M to scale hourly Sonny and Cassie robot workers; valuation undisclosed.
Saab Flies Its Own AI Agents on a Gripen E Fighter Jet
Saab says its in-house AI agents have flown on Gripen E, with an agent autonomously controlling the jet in beyond-visual-range combat scenarios.
Anthropic Launches Message Threads for Faster Claude Agents
Anthropic's Claude API message threads beta sends only new messages each turn, cutting median time to first token about 35% on 500k-1M token requests.
Google Will Auto-Route Gemini 2.5 Pro and Flash Calls Dec. 1
Google has deprecated Gemini 2.5 Pro and 2.5 Flash. From Dec. 1, 2026, API calls to them will automatically route to newer models at their rates.
OpenAI Launches Grid Protectors to Cut Peak Power Use
OpenAI's Grid Protectors Program will have future compute campuses cut power use when grids are strained, starting with up to 1,000 MW in Georgia.
Google, OpenAI and Microsoft Back One AI Training Opt-Out
Google, OpenAI and Microsoft plan to honor one shared robots.txt signal that lets websites opt out of AI training across participating providers at once.
DeepSeek Open-Sources a Super-Agent Coding Prototype
DeepSeek has open-sourced dsh-superagent, an MIT-licensed research prototype of a coding agent that takes requests on GitHub and replies with pull requests.
GenRobot AI Raises $100M Series A+ for Robot Training Data
GenRobot AI, a Beijing robot-training data firm, raised a $100M Series A+ backed by SAIC Motor, Baidu and others to scale human demonstration data.
Apple Intelligence Is Coming to China With Alibaba's Qwen
Apple says Apple Intelligence testing in China starts Nov. 4, with a December launch via iOS 27.3 and Alibaba's Qwen support in Siri and Writing Tools.
Meituan Launches LongCat-2.5, a 1.6-Trillion-Parameter Model
Meituan released LongCat-2.5, a natively multimodal model with 1.6 trillion parameters built for long-horizon coding and agent tasks, via chat and API.
Abu Dhabi Signs Four AI Deals With OpenAI, Including ADNOC
Abu Dhabi entities signed four agreements with OpenAI covering ADNOC, Mubadala, Inception42 and a machine-readable government pilot on UAE-hosted GPUs.
ChatGPT and Codex Will Share One Usage Limit in December
OpenAI says Plus, Pro and Business plans will share one token-based usage allowance across ChatGPT and Codex from December; Instant chat won't count.
OpenAI Expands Agent Monitoring After Hugging Face Incident
How frontier labs are instrumenting autonomous coding and research agents for misalignment in real time.
Mistral Opens Up Large 4, Its 1-Trillion-Parameter MoE Model
Architecture breakdown, active parameter routing, and serving economics for self-hosted enterprise stacks.
Cohere Targets C$7B Series E at C$35.7B Valuation
Why sovereign AI, private VPC deployments, and enterprise retrieval are driving Cohere’s next growth wave.
How Transformers Actually Work — From Attention to KV Cache
A visual, math-grounded walkthrough of self-attention, RoPE, KV caching, and prefill vs decode bottlenecks.
Read the blog
More than 140+ Deep-Dive Articles on AI with Rahish Blog.
Daily engineering breakdowns on frontier LLMs, RAG architectures, agent security, and production benchmarks. Read the latest posts and system notes.
Explore All Blog Posts











