.png&w=256&q=75)
1
1
Pakistan
2+ years of experience
๐ Agentic AI Engineer passionate about building intelligent systems that think, plan, and act autonomously. Currently exploring the frontier of multi-agent architectures, LLM pipelines, and AI-powered automation. ๐ก I build AI apps that solve real problems โ from RAG-based knowledge systems to autonomous agents using LangChain, CrewAI, and the Anthropic Claude API. ๐ ๏ธ Stack: Python | LangChain | CrewAI | FastAPI | Claude API | OpenAI | Vector DBs | HuggingFace ๐ฏ Always hacking, always shipping. Let's build the future together.

APEX Trader is a production-grade autonomous AI trading system built on a multi-agent architecture where five specialized agents work in a coordinated pipeline to analyze, validate, and execute cryptocurrency trades autonomously. The system consists of five agents: the Fundamental Agent analyzes NVT ratios, exchange net flows, and fair value models; the Technical Agent processes EMA crossovers, RSI, MACD, Bollinger Bands, and volume confirmation signals; the Sentiment Agent evaluates Fear & Greed Index and social sentiment scores; the Risk Agent enforces position sizing rules, portfolio heat limits, and R:R ratio thresholds; and the Backtester Agent validates every signal against historical win rates and Sharpe ratios before approval. Each trade requires multi-agent consensus above a configurable confidence threshold (72% day trading / 78% swing trading) before execution. Both day trading (5mโ15m timeframes) and swing trading (4hโ1D timeframes) with dynamically adjusted parameters โ risk per trade, stop-loss placement, take-profit scaling, and trailing stops โ all tuned to expert-level specifications. The APEX self-learning mechanism (evaluate-agent.py) continuously trains on closed trade P&L data, adjusting confidence thresholds autonomously. A self-healing daemon runs 24/7 with automatic error recovery and cooldown logic. The real-time dashboard (built on React/Next.js at port 3201 with a FastAPI backend at port 3202) provides a fully redesigned Agent Analysis Log where every stakeholder โ trader, risk manager, operator, executive โ gets layered information: trade identity, agent pipeline status, per-agent reasoning, strategy prediction with entry/SL/TP targets, course of action, and contextual RSS news feed โ all grouped by trade, pair, or date. The project demonstrates how agentic AI systems can move beyond single-model decision making into coordinated multi-agent architectures that are transparent, auditable, and continuously self-improving.
12 Apr 2026