Skip to content
View faraz-369's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report faraz-369

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
faraz-369/README.md

FARAZ MUBEEN HAIDER

AI SYSTEMS ENGINEER

AGENTIC AI Β· AI SECURITY Β· RELIABILITY & RESILIENCE

I engineer AI systems that are secure, reliable, measurable, and resilient.



01 / ABOUT ME

I build the engineering infrastructure around LLM applications and agentic AI workflows, with a focus on backend architecture, system behaviour, reliability, and security.

My work spans APIs, databases, retrieval pipelines, agent orchestration, testing, and evaluation.

I'm particularly interested in understanding:

  • How AI systems fail and why.
  • How vulnerabilities emerge in agent workflows.
  • How to evaluate LLM and agent behaviour.
  • How to engineer safeguards and recovery mechanisms.
  • How to make AI applications more observable and dependable.

Current role: Full Stack Agentic AI Engineer @ Techloset

Professional direction:

AI Systems Engineering β†’ AI Security β†’ Reliability & Evaluation


02 / ENGINEERING FOCUS

πŸ›‘οΈ AI Security & Risk

  • AI threat surfaces
  • Failure-mode analysis
  • Guardrails and validation
  • Safer agent workflows
  • Security-conscious design

βš™οΈ Reliability & Evaluation

  • Failure injection
  • Automated testing
  • Invariant checks
  • Structured execution traces
  • Reproducible evaluation

πŸ€– Agentic AI Systems

  • Multi-step workflows
  • Tool orchestration
  • LLM integrations
  • Structured outputs
  • RAG applications

πŸ—οΈ Backend Engineering

  • API architecture
  • Authentication & access control
  • PostgreSQL
  • Data integrity
  • Backend integrations

03 / FEATURED ENGINEERING PROJECTS

πŸ”¬ AGENTFAULT LAB

Testing failure and recovery behaviour in multi-step agent workflows.

  • Controlled failure injection: timeouts, exceptions, and malformed responses.
  • Structured execution traces and workflow state recording.
  • Explicit invariant checks.
  • Comparison of no-recovery, retry, and state-aware recovery policies.
  • Reproducible experiment runner and persisted results.

Stack: Python Β· FastAPI Β· Pydantic Β· SQLite Β· Pytest Β· Docker

Evaluation includes a documented 45-run simulated baseline. This is a research prototype, not proof of production-wide agent reliability.


πŸ“š RAG AGENT FAILURE CATALOG

A reproducible collection of failure modes in RAG and agent workflows.

VIEW REPOSITORY β†’

  • Ungrounded answers and citation drift.
  • Retrieval misses and context pollution.
  • Tool loops and silent tool failures.
  • Premature task termination.
  • Numeric and date hallucinations.
  • Reproduction, detection, and mitigation examples.

Stack: Python Β· Pytest Β· LLM Evaluation


πŸ” COMPLIANCERAG

A multi-agent RAG application with groundedness evaluation.

VIEW REPOSITORY β†’

  • Retrieval agent for relevant document context.
  • Generation agent for grounded responses.
  • Critic agent for evaluating generated answers.
  • Citation and groundedness checks.

Stack: Python Β· FAISS Β· Sentence Transformers Β· Hugging Face Β· Gradio


πŸ—„οΈ PORTFOLIOPULSE

A multi-tenant reporting application focused on backend integrity.

VIEW REPOSITORY β†’

  • Tenant-aware data separation.
  • JWT authentication and role-based access.
  • Validated CSV ingestion.
  • PostgreSQL constraints and relational modelling.
  • Approval workflows and audit records.
  • Automated tests, migrations, and CI.

Stack: Python Β· FastAPI Β· PostgreSQL Β· SQLAlchemy Β· Alembic Β· Docker Β· Pytest

34 locally passing tests were recorded on 10 November 2026, including five PostgreSQL integration tests. Uses synthetic data.


πŸ€– SAFELITE

Language-Conditioned Robotic Manipulation via Lightweight LLM Agents

VIEW REPOSITORY β†’

Research direction:

  • Natural-language task planning.
  • Structured robotic action generation.
  • Safety checks before execution.
  • Simulation-based experimentation.
  • Failure handling and self-correction.

Research interests: AI Safety Β· Robotics Β· Autonomous Systems


πŸ“Š DATA QUALITY & ANOMALY DETECTION

A pipeline for dataset validation and anomaly detection.

VIEW REPOSITORY β†’

  • CSV ingestion and validation.
  • Data-quality analysis.
  • Isolation Forest and Z-score anomaly detection.
  • Interactive results and downloadable reports.

Stack: Python Β· Pandas Β· Scikit-learn Β· Gradio

TRY LIVE DEMO β†’


πŸ’Ό HIREMIND AI

An AI-powered career and resume analysis assistant.

VIEW REPOSITORY β†’

  • Resume-to-job matching.
  • Skill-gap identification.
  • ATS-style scoring.
  • Resume optimisation.
  • Cover letter and interview preparation.
  • Application tracking.

Stack: Python Β· Streamlit Β· Groq API


πŸ“ˆ ADVANCED LEADS GENERATION AI

An AI-assisted lead evaluation and prioritisation system.

VIEW REPOSITORY β†’

  • Multi-agent lead assessment.
  • Historical deal context.
  • Structured lead evaluation.

Recognition: IBM Granite Generative AI Hackathon winning team project.


04 / TECHNICAL TOOLKIT

LANGUAGES

BACKEND & DATABASES

AI & MACHINE LEARNING

TESTING & ENGINEERING


05 / PROFESSIONAL EXPERIENCE

Organisation Role Period
Techloset Full Stack Agentic AI Engineer Nov 2026 – Present
MUSTER Product Engineer Jan 2026 – Oct 2026
lablab.ai Applied AI Developer Aug 2024 – Aug 2026
Stanford Code in Place Section Leader 2025 & 2026
1337 Ventures Backend Developer Jun – Sep 2025
NIC Faisalabad AI/Data Engineer Jan – Aug 2024

Selected Contributions

  • NIC Faisalabad: Developed Python ETL and reporting workflows supporting 30+ startups, associated with approximately 60% less manual analyst time.
  • MUSTER: Contributed to an AI-powered real-estate lead qualification prototype.
  • 1337 Ventures: Built backend components for an AI automation SaaS MVP.
  • lablab.ai: Developed AI prototypes involving RAG, LLM integrations, and multi-step workflows.
  • Stanford Code in Place: Supported Python learners through teaching, debugging, and problem-solving.

06 / RECOGNITION

Achievement Recognition
IBM Granite Generative AI Hackathon Winning Team – PolyEns
CS50 Puzzle Day Team Cipher Cracker – 9 puzzles solved
Stanford Code in Place Section Leader – 2025 & 2026
BICON Accelerator, NUML BillBachao selected for incubation
AlgoVerse Research Program Accepted participant – 45% merit scholarship

07 / CURRENT LEARNING

My current engineering focus is on developing deeper expertise in:

  • LLM and agent failure modes.
  • AI security and threat surfaces.
  • Guardrails and safer tool execution.
  • Reproducible testing and evaluation.
  • Authentication and access control.
  • Database integrity and PostgreSQL.
  • Observability and distributed systems.

08 / EDUCATION

Bachelor of Science in Software Engineering

National University of Modern Languages (NUML)
2022 – 2026


LET'S CONNECT

Interested in AI engineering, agentic systems, AI security, and reliable intelligent software.




Building AI systems whose behaviour can be tested, understood, and trusted.

Pinned Loading

  1. rag-agent-failure-catalog rag-agent-failure-catalog Public

    Catalog of silent failures in RAG systems and AI agents, with reproduce, detect and mitigate code

    Python 10

  2. ComplianceRAG ComplianceRAG Public

    Multi-agent RAG with a critic agent that scores groundedness and flags hallucinations in real time. FAISS + sentence-transformers + Gradio.

    7

  3. agentfault-lab-Web agentfault-lab-Web Public

    A reproducible fault-injection and recovery testing lab for AI agents.

    Python 2

  4. SafeLite SafeLite Public

    Language-Conditioned Robotic Manipulation via Lightweight LLM Agents.The repository is designed to support experimentation around planning, safety reasoning, execution, simulation, and evaluation w…

    Python 7

  5. data-quality-pipeline data-quality-pipeline Public

    Enterprise-grade anomaly detection and data governance system β€” deployable in one click on Hugging Face Spaces.

    5

  6. portfoliopulse portfoliopulse Public

    A multi-tenant portfolio operations platform built with FastAPI, PostgreSQL and Streamlit, featuring structured reporting workflows, data validation, analytics and auditability.

    Python 1