Skip to content
View neomond's full-sized avatar
💌
Amor Fati
💌
Amor Fati

Block or report neomond

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
neomond/README.md

Nazrin Atayeva: iOS engineer building AI and perception systems iOS engineer with 3+ years shipping production banking and telecom apps. MSc AI for Engineering, University of Sheffield. I work across three layers of an intelligent product: the app people use (iOS, 1M+ users, zero rollbacks), the agent that reasons (LLM agents, tools, guardrails), and the model that sees (3D perception, sensor fusion, visual geometry on ADAS). Tech stack. iOS and mobile: Swift, SwiftUI, UIKit, Xcode, Combine, RxSwift, Core Data, Realm, CoreML, ARKit, SPM, Tuist, React Native, Flutter, Dart, Android. AI agents: Python, FastAPI, Docker, PostgreSQL, OpenTelemetry, OpenAI, Anthropic and Gemini APIs, Ollama, Hugging Face, LiteLLM, vLLM, LangGraph, LangChain, LlamaIndex, MCP, Pydantic, RAG with pgvector, Qdrant and FAISS, Ragas, DeepEval, Langfuse, LangSmith, guardrails. Perception: PyTorch, TensorFlow, OpenCV, NumPy, Open3D, BEVFusion, PointPillars, YOLO, nuScenes, sensor fusion. Engineering and web: Git, GitHub Actions, GitLab CI, TDD, Clean Architecture, JavaScript, TypeScript, Node.js, React, Next.js, GraphQL, Go, Firebase, MongoDB, SQLite, Figma.

Pinned Loading

  1. lightweight-bev-adas lightweight-bev-adas Public

    Lightweight BEV perception for ADAS: compressing camera-LiDAR fusion via knowledge distillation, pruning, and quantization. YOLO11 + PointPillars student distilled from BEVFusion teacher. MSc Disse…

    Python

  2. f1-points-predictor f1-points-predictor Public

    Binary classifier predicting whether an F1 driver finishes in the points (top 10). Built with leakage-safe feature engineering, TimeSeriesSplit cross-validation, GridSearchCV, and a Streamlit demo.

    Python

  3. f1-race-engineer-agent f1-race-engineer-agent Public

    Agentic AI race engineer for Formula 1 - tool-using LLM that reads live timing data lap-by-lap, fits tyre degradation curves, simulates pit windows, and makes radio calls. Cross-validated across 20…

    Python

  4. f1-sensor-anomaly-detection f1-sensor-anomaly-detection Public

    Multi-model anomaly detection benchmark on F1 car telemetry — Isolation Forest vs One-Class SVM vs LOF on 16 sensor channels with realistic failure modes

    Python

  5. mnist-cnn-classifier mnist-cnn-classifier Public

    CNN achieving 99.08% accuracy on MNIST with PyTorch — complete ML pipeline with training, evaluation, error analysis, and feature visualization.

    Python

  6. SerenityYoga SerenityYoga Public

    Yoga app in react native

    TypeScript 1