AI & ML
LLMs · RAG · AI agents · multi-agent · NLP · prompt eng
Building intelligent systems that ship.
I'm Ansar — an AI/ML engineer working on the seam between AI-Agents, System Architecture, rapidly R&D ing new AI-driven workflows, and the kind of product thinking that makes sure the businesses actually run on. Currently a junior AI developer at Webdura Technologies, building AI products and agent assistants for traditional industries.
01 / About
A short brief.
Who's behind the keyboard.
I finished my M.S. in Computer Science in May 2025 and have spent the time since building intelligent systems that actually ship — agentic workflows, RAG pipelines, and LLM-powered applications wired for production scale, not demos.
Today I'm a junior AI developer at Webdura Technologies, architecting LLM-powered solutions with LangGraph, RAG, FastAPI, AWS, and Docker — cloud-native, multi-tenant AI platforms and agent assistants that automate workflows for traditional industries.
I sit close enough to product to map industry pain points to AI primitives before they hit a spec — and broad enough across domains (recruitment, retail, satellite, content moderation) to know which ones are actually worth solving.
I care about systems that survive the boring parts of production — latency budgets, drift, cost ceilings, the request that arrives in a language you didn't plan for. The rest is decoration.
Years
0+
building production AI
Impressions
0K
organic growth led at Bookdio
Languages
0
human · plus Python & SQL
Roles
0
across AI · CV · BI · agents
02 / Work
Where I've been operating.
Roles, in reverse-chronological order.
-
2026 → present
Junior AI Developer
Webdura Technologies
Designing AI architectures across agentic workflows, RAG pipelines, and LLM-powered systems — taking production-ready AI solutions from prototype through deployment across diverse business domains.
↳ build Engineer intelligent automation pipelines spanning conversational AI and business process orchestration.
↳ platform Develop cloud-native AI platforms with multi-tenant architecture, reliability, and scalability built in.
-
2025 → 2025
AI/ML Developer
Teamup Consultants
Rapid-prototyped AI workflows to compress idea-to- execution, with cloud-native components and intelligent authentication slotted in cleanly.
↳ focus Generative AI for recruitment across the Gulf & Middle East — workflows sculpted for scalability and high-performance global rollout.
-
2025 → 2025
AI Module Lead
Tienext Corporation
Owned NLP infrastructure for sentiment + safety, deployed on AWS for production scale.
↳ key Multilingual hate-speech detection pipeline (Python · NLTK · real-time moderation).
-
2025 → 2025
AI Developer
Zeex AI
Generalised computer-vision models for theft detection, smart traffic analysis, and satellite imagery.
↳ key Few-shot learning CV stack on Vision-Transformer backbones.
-
2024 → 2025
Team Manager · Content / Data
Bookdio
Led a team using AI-driven analytics to optimise content workflow and discovery.
↳ key Grew organic page impressions from 2.43K → 477K in a year.
In good company
03 / Stack
Capability matrix.
What I reach for. Short list.
Agentic & LLM
LangGraph · LangChain · MCP · LLM engineering
Cloud & MLOps
AWS · Docker · CI/CD · MLOps · Redis · Celery
Backend
Python · FastAPI · Flask · REST · PostgreSQL
Data & BI
SQL · Pandas · Power BI · Tableau · dashboards
Practice
Product thinking · Agile · cross-functional leadership
04 / Case studies
Problems, shipped.
A short index of engagements where AI moved real numbers. Full write-ups on request.
-
C/01
Kaizen-RAG — self-improving retrieval
A self-improving RAG framework with disagreement-based active learning and an LLM-as-judge eval loop (RAGAS) — faithfulness climbed 72% → 91% across 3 automated cycles with zero manual re-labeling.
26 -
C/02
Polymath-Agent — multi-agent research
A domain-agnostic multi-agent research & reasoning pipeline (LangGraph · RAG · FastAPI) with Mixture-of-Agents routing across 3 domains — cutting synthesis time 60% and LLM cost 40% vs baseline.
26 -
C/03
MCP-Forge — MCP server generator
An open-source toolkit that compiles a single YAML spec into a production-ready Model Context Protocol server — eliminating ~200 lines of boilerplate per implementation with built-in mock testing.
26 -
C/04
LLM-Lens — LLM observability
A lightweight LLM observability stack on OpenTelemetry, Prometheus, and Grafana — tracking 10 key metrics through a drop-in decorator with single-command Docker deployment.
25
05 / Contact
Have something worth building?
Let's talk.
I'm engaged full-time at Webdura, but I always make room for interesting collaborations, advisory chats, and product problems worth solving. The fastest path is email.