Applied systems and serious learning

Learn the systems behind
modern intelligence.

Deep technical courses and focused AI products for engineers who want to understand what they build, not just call an API.

All courses are currently open for self-paced learning
FIGNIX LEARNING MAP12 deep dives
Learn by buildingconcept → code → operations
STREAMINGINFERENCESEARCHLAKEHOUSEVECTORSEVALSDURABILITYRAGLLM BUILDSARVAMAGENTSPGVECTOR
First principlesRunnable labsProduction thinking
12complete technical courses
100+lessons and practical labs
2applied AI products
0surface level shortcuts

Product portfolio

AI systems built for consequential work.

Focused products that make autonomous systems more useful, controlled, and accountable.

Fignix product 01

Sentinel turns risk signals into explainable action.

Real-time fraud decisions, autonomous investigation, human approval, and compliance-ready evidence in one operational system.

Meet Sentinel
LIVE RISK WORKFLOWHEALTHY
01Transaction decision12 ms
02Threat enrichmentactive
03Evidence correlation6 sources
04Human approvalready
NEXT ACTIONPrepare the investigation summary for reviewDecision evidence attached

Fignix product 02

FignixOS gives agent fleets a governance layer.

Run coding agents in isolated workspaces, enforce task budgets, control data access, and keep a complete record of what every agent did.

Explore FignixOS
FIGNIXOS / AGENT FLEET 3 ACTIVE
WORKING 2
Secure auth boundaryClaude Code · sandboxed14.2k / 30k tokens
Add retrieval testsOpenCode · sandboxed8.1k / 20k tokens
NEEDS YOU 1
Review schema migrationBudget paused safely20k / 20k tokens
READY 1
Fix flaky worker testCI passed · PR readyEvidence attached

Course library

Choose a system.
Go all the way down.

Each course combines conceptual depth, visual explanation, code, labs, and the operational details that shorter tutorials leave out.

01K×F

Distributed data

Kafka and Flink

Build reliable stream processing systems from partitions and event time to checkpoints, state, and production operations.

85 lessons, labs and capstonesExplore course →
02LLM

AI infrastructure

LLM Inference Optimization

Understand high performance serving through KV cache economics, batching, kernels, scaling, and production tradeoffs.

Foundations, techniques and labsExplore course →
03SOL

Search engineering

Apache Solr

Master search systems from schema and relevance to SolrCloud, vector retrieval, hybrid search, LTR, and operations.

20 modules and extensive labsExplore course →
04ICE

Lakehouse engineering

Apache Iceberg

Learn table format internals through metadata, snapshots, evolution, catalogs, row level changes, and maintenance.

28 labs and three capstonesExplore course →
05QDR

Vector databases

Vector Search with Qdrant

Engineer accurate vector retrieval through filtering, hybrid search, HNSW tuning, multitenancy, distributed operation, and recovery.

Python labs and a RAG capstoneExplore course →
06EVAL

AI quality engineering

AI Evals

Evaluate LLM, RAG, conversational, tool-using, agentic, MCP, safety, release, and production behavior with defensible evidence.

23 chapters, Python labs and a continuous capstoneExplore course →
07DUR

Agent reliability engineering

Durable Agents

Master Temporal and LangGraph independently, then combine their histories, checkpoints, retries, human review, and idempotent effects.

34 chapters and 50 verified Python labsExplore course →
08RAG

Knowledge and retrieval engineering

RAG Engineering

Build governed retrieval systems from parsing and hybrid search to grounding, citations, evaluation, security, and production operations.

41 chapters and 48 verified Python labsExplore course →
09GPT

Language model foundations

Build an LLM from Scratch

Implement a small GPT-style language model from tokenization and causal attention to training, checkpoints, and text generation.

10 modules and 31 verified Python labsExplore course →
10SAR

India-first multimodal AI

Sarvam AI Engineering

Build multilingual text, speech, voice-agent, and document systems with explicit evaluation, safety, privacy, and production contracts.

19 chapters, 52 Python labs and three capstonesExplore course →
11AGT

Autonomous systems engineering

Agentic AI Engineering

Build bounded agents from the Python control loop through tools, memory, planning, protocols, security, durability, evaluation, and production.

29 chapters, 90 Python labs and three capstonesExplore course →
12PGV

PostgreSQL vector search

Vector Search with pgvector

Engineer exact and approximate similarity search with HNSW, IVFFlat, filtering, hybrid retrieval, recall measurement, and PostgreSQL operations.

23 chapters, 52 verified labs and three capstonesExplore course →

Start with the system you need

Build deeper understanding.
Make better engineering decisions.

Choose a course and start learning now. Every topic is designed to connect theory, implementation, and operations.

Explore the library