Skip to main content
Ahmed Doghri Logo Image
Ahmed Doghri

Hi there! I'm Ahmed Doghri!

ML engineer making machine learning fun and accessible! Stick around for tips, insights, and AI stories!

About Me With a focus on innovation and real-world impact, I'm here to share my journey, expertise, and insights into the world of artificial intelligence.

Get to know me!

Hello! I'm Ahmed Doghri, a Senior AI Engineer with 8+ years shipping end-to-end production ML systems. I specialize in RAG pipelines, multi-agent orchestration, and LLM evaluation harnesses (RAGAS, DeepEval). My track record includes measurable impact in regulated domains such as pharma, fintech, and B2B—from building production Slack RAG assistants with 94% citation precision to architecting 7 production LLM agent pipelines for FDA IND submissions that reduced hallucination rates by 60%. I thrive at the intersection of cutting-edge AI and real-world business impact. Let's connect if you're interested in leveraging AI for transformative growth!

Professional Timeline:

  • Idea Boundary - Founder and Principal AI Engineer (Independent Consulting), building production RAG systems, multi-agent orchestration, and churn prediction pipelines with measurable business impact.
  • Weave - Senior AI Engineer, focused on automating regulatory submissions using LLMs
  • BenchSci - Senior ML Engineer, advanced biomedical text enrichment using LLMs and transformer-based models.
  • IBM - Senior Data Scientist & Consultant, developed NLP pipelines and deployed chatbot solutions, optimizing processes for banking and retail clients.
  • Scotiabank - Product Owner, launched an AI bot for automated negative news detection, improving risk management and reducing manual monitoring by 75%.
  • Ford Motor Company - Research Assistant, developed high-precision misfire detection and DAQ systems for automotive signal processing.

Download Resume

My Skills

LangChain
LangGraph
LlamaIndex
OpenAI
Azure OpenAI
Anthropic
vLLM
TensorRT
Hugging Face
RAG (Retrieval-Augmented Generation)
Multi-Agent Orchestration
Agentic AI
Hybrid Retrieval
Prompt Engineering
Function Calling
Context Engineering
AI Safety & Guardrails
PyTorch
TensorFlow
spaCy
Scikit-Learn
XGBoost
BERT
LoRA/PEFT
Fine-Tuning
NLP
FAISS
Pinecone
Milvus
Neo4j
Elasticsearch
PostgreSQL
MLflow
Kubeflow
Vertex AI
SageMaker
Bedrock
Docker
Kubernetes
Kafka
Flink
Spark
dbt
CI/CD
AWS
GCP
Azure
RAGAS
DeepEval
OpenTelemetry
Phoenix
Hallucination Detection
Token Cost Monitoring
Python
SQL
R
C/C++
Contact

Projects Take a peek at some of my projects! Feel free to click around and see what I've been building lately!

VectorMorph Screenshot

VectorMorph

VectorMorph is a lightweight, Flask-powered animation converter that transforms SVG frames into animated WebP or GIF files.

Case Study
ATS Proof Resume Generator Screenshot

ATS Proof Resume Generator

An AI-powered tool that optimizes resumes for Applicant Tracking Systems, helping job seekers get past algorithmic filters and land more interviews.

Case Study
E-book Converter Screenshot

E-book Converter: My Files, My Rules

A self-built, local e-book converter (EPUB, MOBI, PDF) created in one hour to bypass the friction and fees of online tools. Take back control of your files.

Case Study
vllm-cost-router Screenshot

vllm-cost-router

A cost and latency aware LLM gateway that routes by complexity, caches repeats, and batches concurrent requests. 73% lower cost, 73% lower p95 latency, reproducible with one command.

Case Study
guardrail-gate Screenshot

guardrail-gate

A guardrail service that catches PII leaks and ungrounded claims in a single pass, with one allowed/blocked decision and the reasons attached.

Case Study
tablextract Screenshot

tablextract

Extracts tables from documents that mix prose and data with no explicit markup, and answers questions with a citation to the exact row and column.

Case Study
citebench Screenshot

citebench

A benchmark quantifying what hybrid retrieval and reranking actually buy you in citation-grounded RAG. Citation precision 62% to 88% on adversarial content.

Case Study
churnfm Screenshot

churnfm

A churn classifier that detects prediction-distribution drift with PSI and retrains automatically before precision rots.

Case Study
taggate Screenshot

taggate

A confidence-gated tagging pipeline that auto-tags the confident cases and escalates only genuinely ambiguous items to a human.

Case Study
agentmem Screenshot

agentmem

Bounded, self-consolidating long-term memory for LLM agents that stays under a fixed budget instead of growing forever.

Case Study
rubricagent Screenshot

rubricagent

Self-evolving LLM-as-judge rubrics, learned from outcomes instead of a hand-written guess. Rubric quality (AUC) 0.77 to 1.00 after one evolution pass.

Case Study
clarifyrag Screenshot

clarifyrag

A search agent that asks a clarifying question only when retrieval is genuinely ambiguous. 100% accuracy while asking 38% fewer questions than always-asking.

Case Study

Contact You can slide into my DMs anytime, but to keep it easy-breezy, just pop me an email using the form below!