LangGraph
Built browser-integrated workflow sidekicks and the autonomous agent loops that automate client comms and vendor matching at Wanhar Impex.
Muhammad Ahsan · Riyadh, Saudi Arabia
I design and deploy secure, autonomous multi-agent systems — LangGraph, CrewAI, and MCP, running in production.
Autonomy isn't prompted. It's engineered — part by part.
The orchestration pattern I run in production. This isn't a mockup — it's the real architecture pattern behind my production multi-agent systems.
The orchestration stack I build with — each grounded in real projects and certifications.
Built browser-integrated workflow sidekicks and the autonomous agent loops that automate client comms and vendor matching at Wanhar Impex.
Engineered autonomous agent teams that draft contracts and coordinate multi-step business workflows.
Designed multi-agent conversation networks and swarms for collaborative task decomposition.
Deployed multi-agent networks and orchestrators with Claude Code subagents, driving automated feature development wired into Jira and GitHub.
Orchestrated complex multi-agent systems and hand-off logic across specialized worker agents.
Built production multi-agent loops on AWS with Lambda, SQS, and Aurora Serverless for scale.
Integrated multi-server MCP environments so agents reach tools, data, and each other through a shared protocol.
Composed RAG chains and production interfaces over open-source vector datastores.
Instrumented LLM observability, cost tracking, and guardrails across production agent runs.
Fine-tuned and served open-source models; ran QLoRA on top of the HF ecosystem.
Runs high-velocity delivery with Claude Code, Cursor, and MCP — context managed via AGENTS.md and CLAUDE.md.
Cut LLM cost and latency with prompt/context compression, caching, and token budgeting — measured and tuned through LangFuse.
Run production LLM operations end to end — observability, cost tracking, guardrails, and evals — alongside classic MLOps.
Ship agents to production on AWS with Bedrock AgentCore, Lambda, SQS, and Aurora — automated via Terraform and GitHub Actions.
My agentic workflow methodology for shipping features fast with coordinated coding-agent teams.
Used Gastown to build and wire multi-agent workflows.
Wanhar Impex · Director & AI Engineering Lead
Shipment request enters the graph as typed state.
Goal decomposed into retrieve → draft → review → execute.
RAG over the vendor + freight vector store.
Bilingual RFQ and contract terms generated from context.
Security & privacy guardrails redact and approve.
Approved action dispatched through MCP tool servers.
Tokens, cost, and latency logged via LangFuse.
A real production workflow — condensed. Automates vendor sourcing, outreach, and contract drafting with a security gate on every hand-off.
A fully offline personal AI assistant running local LLMs at zero cloud cost.
A civilization sim where NPCs reason with local LLMs and remember via SQLite.
A high-performance scraper automating B2B lead generation and business auditing.
An ML pipeline predicting subscriber churn to power retention campaigns.
A replay study of a vehicle's keyless-entry signal using a HackRF One.
Multi-agent networks, swarms, and autonomous loops in production.
From inference to training — RAG, fine-tuning, and vector stores.
Serverless AI on AWS, Azure, and GCP — automated with IaC.
Classical ML, deep learning, and statistical modeling.
High-velocity delivery with agentic coding tools.
Including Google Advanced Data Analytics, Python 3 Specialization, EHE, and Agentic AI tracks.
TryHackMe leaderboard rank — backed by EC-Council Ethical Hacking Essentials and TryHackMe security certifications.
Across agentic AI, machine learning, RF security, and IoT systems.
Leading AI, automation, and software delivery at Wanhar Impex since 2020.
Enterprise-grade agentic engineering: secure multi-agent systems, RAG over your private data, and custom LLM integrations — grounded, observable, and deployed serverless on AWS, Azure, or GCP.
39 documented certifications across agentic AI, data science, security, and engineering — the foundation under the work.
The foundations under the AI — security, data, and hardware.
Ethical hacking, forensic analysis, and secure-by-design pipelines.
Google-certified advanced analytics and statistical modeling.
RF communication, SDR, and physical sensor integration.
Available for AI Engineer, Generative AI Engineer, Machine Learning Engineer roles — on-site in Riyadh or remote worldwide.