Afraz Ahmed

AI Engineer · Backend · Problem Solver

I'm a software engineer, trying to get LLMs and agents to behave and coordinate themselves in applications.

I typically use RAG pipelines and agent workflows to get there, but always down to talk tools if you're curious what works.

Feel free to reach out or send me an email if you'd like to chat about my work, need some consultation, or just want to talk.

afraz3301@gmail.com / LinkedIn / GitHub

Work ›

Inspection AI Applivity

Agentic, voice-driven inspection platform for RealWear devices, combining offline on-device speech with hybrid document retrieval for hands-free field use.
Incident AI Applivity

Production voice-driven incident reporting system across 9+ languages, cutting incident logging time from hours to under 2 minutes.
Video Analysis AI Applivity

Video analysis pipeline that chunks and indexes training footage for fast keyword and semantic search across a large library.
PDF & Document Intelligence Pipeline Applivity

Dual-agent extraction and verification architecture that reduces hallucination rates in unstructured document parsing.
Rapticore Applivity

Cloud security and data governance SaaS platform with multi-cloud pipelines, a Neo4j graph layer, and automated compliance checks.
Engineering Memory OS Hackathon, Aug 2026

AI-powered institutional memory platform integrating GitHub, GitLab, Slack, and Jira, built for a CockroachDB × AWS hackathon.
Client Facing Software Engineer Remotebase

Translated business requirements into working software on the Snapdev (now Amber.ai) platform as primary technical point of contact.
Full Stack Engineer Thathal I&TS

Built Google Ads API connectors and React/TypeScript dashboards, and co-developed a containerized microservices SaaS platform.

About ›

Generative AI & LLM Engineering

OpenAI API, Azure OpenAI (GPT-4, GPT-4.1, GPT-5 mini), RAG, LangChain, LangGraph, LlamaIndex, embeddings, prompt engineering, LLM-as-judge evaluation, model evaluation and benchmarking

Agentic AI & Automation

Multi-agent architectures, AI agents, chatbots, copilots, tool calling, workflow orchestration, human-in-the-loop review, MCP integrations, n8n

Machine Learning & NLP

Python, TensorFlow, PyTorch, Scikit-learn, NLP, deep learning fundamentals

Search & Retrieval

Azure AI Search, Pinecone, FAISS, ChromaDB, BM25, fuzzy search, semantic search, chunking/indexing

Voice & Conversational AI

Azure Speech SDK (STT/TTS), sherpa-onnx (Whisper, Piper), on-device/offline speech, multilingual (9+ languages)

Backend & Cloud

Node.js, Python, REST APIs, JWT/OAuth2/OIDC, microservices, Azure, AWS, GCP, Neo4j

Bachelor of Software Engineering, FAST-NUCES 2020 – 2024

AWS Certified Cloud Practitioner

Writings ›

Articles, LinkedIn posts, and research notes will be collected here soon.