Thoughts, learnings, and insights from my journey in tech.
A comprehensive enterprise field guide distilled from Securiti's AI Security & Governance certification. Covers AI security, model discovery, NIST AI RMF, Gartner TRiSM, OWASP Top 10 LLM Risks, LLM Firewalls, and global regulations like the EU AI Act.
The grand finale of our AI Engineering masterclass series. Master LLM Evaluation Suites (Evals), LLM-as-a-Judge, Latency Optimization (TTFT, TBT, vLLM), Semantic Caching, and Observability.
Part 4 of our AI Engineering masterclass series. Explore autonomous AI Agents: ReAct execution loops, Function Calling mechanics, Multi-Agent Orchestration, E2B Sandboxing, and Prompt Injection defenses.
Part 3 of our AI Engineering masterclass series. Dive deep into Retrieval-Augmented Generation: Chunking algorithms, Vector Embeddings, HNSW vs IVF indexing, Hybrid Search (BM25 + Dense), RRF, and Cross-Encoder Reranking.
Part 2 of our AI Engineering masterclass series. Explore advanced Prompt Engineering (CoT, Tree-of-Thoughts), Tokenizer mechanics, Context Window dynamics, and guaranteed Structured JSON Outputs with Zod and Pydantic.
The first in a 5-part masterclass series on AI Engineering. Deep dive into Foundation Model architectures, Pre-training vs SFT vs RLHF/DPO, GPU VRAM calculations, Quantization (GGUF, AWQ), and Build vs Buy.
The grand finale of our DDIA masterclass series. We synthesize the entire book to explore Unbundling the Database, Derived Data vs Source of Truth, Lambda/Kappa architectures, End-to-End Correctness, and Data Ethics.
Part 4 of our DDIA masterclass series. Explore MapReduce, Spark, Distributed Join Algorithms, Log-Based Stream Processing (Apache Kafka), Event Sourcing, and Change Data Capture (CDC).
Part 3 of our DDIA masterclass series. Delve into ACID properties, MVCC, Weak Isolation Levels, Concurrency Bugs (Write Skew, Phantoms), Two-Phase Commit (2PC), and Distributed Consensus.
Part 2 of our DDIA masterclass series. Explore the deep mechanics of Distributed Data: Single-Leader, Multi-Leader, Leaderless Replication, Quorum Math, Replication Lag anomalies, and Partitioning.
The first in a 5-part masterclass series on Designing Data-Intensive Applications. Deep dive into Reliability, Scalability, Maintainability, Data Models (Relational, Document, Graph), and Storage Engines (LSM-trees vs B-trees).
A comprehensive deep dive into the Transformer architecture from the groundbreaking 'Attention Is All You Need' paper. Learn about Self-Attention, Multi-Head Attention, Positional Encoding, and why Transformers revolutionized NLP.
No posts found with this tag.
