Tarek Masryo
AI Engineer
I build production ML and Generative AI systems with measurable behavior, explicit failure modes, and reliable operation under real-world constraints.
AI Systems Engineering; Model Serving, APIs and AI Infrastructure; RAG, Retrieval and
Knowledge Systems; AI Agents, Tool Use and Execution; Evaluation, Benchmarking and System
Reliability; AI Operations, Observability and Reliability.
View CV About Me
I'm Tarek Masryo, an AI Engineer building production ML and Generative AI systems across model serving, retrieval, agents, evaluation, and operations.
I work across software engineering and machine learning. I integrate models with APIs and backend services, build model-serving and retrieval infrastructure, develop RAG and agent workflows, and create the evaluation, benchmarking, and operational tooling needed to run them reliably.
I build AI systems end to end, and model quality is only one part of the problem. Data, preprocessing, retrieval, tool execution, application logic, latency, cost, and failure handling all shape production behavior. When something breaks or degrades, I trace the execution path across these layers to identify where the problem actually originates.
Evaluation and measurement are part of the engineering loop, not a final checkpoint. I use reproducible workflows, executable checks, failure analysis, and observability to compare changes and diagnose regressions, while making trade-offs across quality, latency, cost, reliability, security, and maintainability. I prefer clear interfaces, explicit failure modes, and systems that are straightforward to test, operate, and evolve.
Featured Work
Four public systems showing how I build, evaluate, and operate reliable systems beyond the prototype stage.
Fraud Risk Ops Platform
Model serving · policy decisions · audit trails · operations.
Operational flow: score → policy → review → audit → monitoring
RAG QA Command Center
Retrieval diagnostics · trace inspection · configuration comparison.
Evidence: 3,824 offline QA evaluation runs · 93,375 retrieval events
LLMOps Telemetry Command Center
Reliability · latency · cost · routing · triage.
Evidence: 9,000 offline interactions · 1,595 sessions
Selected Projects
Additional work across applied ML, computer vision, analytics, and decision systems.
NLP Workspace
Advanced ML Sentiment Lab
Text classification · model comparison · ROC-AUC/PR-AUC evaluation · threshold tuning · error analysis.
Healthcare ML
Hospital Deterioration — Next 12h Early Warning
Patient-level leakage controls · Average Precision and ROC-AUC · alert-policy trade-offs.
Decision App
Short Video Intelligence Dashboard
Virality scoring · engagement KPIs · creator comparison · timing patterns · segment benchmarks.
Computer Vision App
Old Photo Restorer
User-facing image-restoration app with before/after review, presets, and batch ZIP export.
Dashboard
EV Charging Dashboard
Interactive EV infrastructure dashboard for coverage analysis and fast-DC allocation scenarios.
ML Pipeline
Pima Diabetes Pipeline
Schema validation · calibrated probabilities · threshold trade-offs.
Capabilities
Building production AI systems across model integration, retrieval, agents, evaluation, serving, and reliable operation.
Production ML Systems
Build reproducible ML systems from data validation and training through versioned artifacts, calibrated predictions, decision policies, and reliable inference.
RAG & Retrieval Systems
Build ingestion, indexing, hybrid retrieval, reranking, grounding, and evaluation pipelines with measurable retrieval and answer quality.
AI Agents & Tool Execution
Design controlled agent workflows with explicit execution steps, structured tool calls, safeguards, failure handling, and traceable intermediate behavior.
AI Evaluation & Benchmarking
Build executable evaluations and benchmarks to measure model, retrieval, and agent behavior, surface failure modes, and catch regressions before release.
AI APIs & Model Serving
Design typed APIs and inference services for ML and LLM workloads with versioned artifacts, background jobs, health and readiness checks, and explicit runtime contracts.
AI Operations & Reliability
Track quality, latency, cost, drift, routing, and failures so systems can be compared before rollout and monitored reliably after release.
Technical Stack
A focused set of tools and practices for building, evaluating, serving, and operating production AI systems.
Core Stack
A focused core stack for building and operating production AI systems.
Python SQL FastAPI · Pydantic v2 PostgreSQL · pgvector Redis PyTorch scikit-learn Hugging Face Transformers Sentence Transformers LangGraph · MCP Docker · Docker Compose AWS Git · Linux pytest · ruff Prometheus · Grafana · OpenTelemetry GitHub Actions
Explore Engineering Toolkit
AI & Model Engineering
Training, inference, fine-tuning, explainability, and decision quality.
PyTorch TensorFlow Keras scikit-learn XGBoost LightGBM Hugging Face Transformers Sentence Transformers LLM Fine-tuning SHAP ONNX ONNX Runtime Model Evaluation Calibration Threshold Tuning Error Analysis
RAG, Agents & Evaluation
Retrieval, orchestration, tool execution, benchmarking, and evaluation.
RAG Hybrid Retrieval Reranking Embeddings Vector Search pgvector FAISS LangGraph LlamaIndex LangChain Tool Use Code Execution MCP Context Engineering LLM Evaluation Agent Evaluation Retrieval Evaluation Benchmark Design Executable Checks Failure Analysis RAGAS DeepEval Ollama vLLM OpenAI API Anthropic API Google Gemini API
APIs & Application Systems
Serving AI capabilities through reliable software interfaces.
FastAPI Pydantic v2 SQLAlchemy Alembic REST APIs Redis RQ Background Jobs Model Serving Schema Validation
Data & Retrieval Infrastructure
Storage, validation, indexing, and data workflows.
PostgreSQL pgvector Redis DuckDB SQLite NumPy Pandas Polars Pandera pypdf unstructured Document Parsing Chunking Metadata Extraction
Reliability, Cloud & AI Operations
Testing, deployment, observability, cloud infrastructure, and production behavior.
AWS Docker GitHub Actions CI/CD pytest ruff mypy MLflow Prometheus Grafana OpenTelemetry Structured Logging Tracing Model Monitoring Latency/Cost Monitoring Health & Readiness Checks Caddy Nginx
Analysis & Operator Interfaces
Analysis, debugging, review, and operational interfaces.
Jupyter Plotly Matplotlib Seaborn Streamlit Gradio Chainlit TypeScript JavaScript React Tailwind CSS
Working With Me
How I scope, build, evaluate, and hand off production AI systems.
What kind of work do you take on?
I work on production ML and Generative AI systems, including RAG, AI agents, model serving, evaluation, AI APIs, and reliability. I can build new systems or help move existing prototypes toward production.
How do you approach an existing system?
I first map the architecture, data flow, dependencies, constraints, and known failure points. I preserve what already works, simplify where useful, and make changes that can be tested, measured, and rolled out safely.
How do you decide when something is ready?
I define measurable acceptance criteria around what matters for the system: quality, retrieval performance, failure rates, latency, cost, reliability, and review load. A good model metric alone is not enough.
What does delivery include?
Usually code, tests, configuration, reproducible setup, evaluation artifacts, documentation, and deployment support. Monitoring and review workflows are included when the system needs them.
How do you handle reliability?
I use explicit contracts, validation, regression tests, versioned artifacts, structured logging, health checks, and clear failure behavior so problems are easier to detect, reproduce, and diagnose.
What happens after delivery?
After delivery, the system should be clear to use, easy to maintain, and straightforward to operate. I document the important assumptions and known limits, and I can stay involved with monitoring, stabilization, or further improvements when needed.
Contact
Let's Build What's Next
I'm open to remote AI engineering roles, consulting work, and selected technical collaborations across production ML and Generative AI systems.
Send me a message directly, or connect with me on LinkedIn.
- Opportunities
- Full-time, part-time, or contract
- Collaboration
- Interesting projects and research
- General Inquiries
- Feel free to reach out