Machine Learning Engineer · Local-first AI & semantic search

Muhd Uwais

Machine Learning Engineer building practical, local-first AI systems and semantic search that actually ships.

I solve data-intensive problems by keeping inference local. By replacing cloud-dependency with efficient, on-device pipelines, I deliver systems that are faster, more private, and more reliable than traditional alternatives.

View Projects Contact Me

About

Engineering
useful ML systems

I'm building developer tools that work offline-first: semantic code search that understands intent (Ziv), AI-assisted Python type annotation for legacy codebases (TypePatch), and speaker recognition that runs entirely on-device (EchoID).

No cloud dependencies. No API keys. Just systems that ship and solve problems people actually have.

0+
Open-source projects
0+
ML models deployed
0+
Years focused on ML
∞
Lines of curiosity

What I actually build

  • Local-first ML tools that respect latency, bandwidth, and privacy constraints.
  • Semantic search pipelines combining embeddings, FAISS, and clean APIs.
  • Efficient inference systems using ONNX for practical deployment.

Skills

Capabilities across
ML, systems & infra

Machine Learning / AI

Python TensorFlow / Keras Embeddings & semantic search CNNs Ranking & retrieval Model evaluation

Backend / Systems

FastAPI Django ONNX runtime RESTful APIs Clean architecture

Tools / Infra

Git & GitHub Docker Linux CI/CD basics Monitoring & logging

Projects

Systems built for
real-world problems

All projects on GitHub

Ziv

Local-First Semantic Code Search

Problem: Traditional code search relies on keyword matching, making it difficult to locate code by intent, behavior, or meaning.

  • Performs semantic search over local repositories using vector embeddings and FAISS indexing.
  • Delivers low-latency, intent-aware retrieval without cloud services or external APIs.
  • Built as a production-oriented developer tool with FastAPI and ONNX Runtime for efficient local inference.
Python FAISS ONNX Runtime FastAPI Sentence Transformers
Featured Active
In Development

TypePatch

AI-Assisted Python Type Annotation

Legacy Python codebases often lack type annotations, making static analysis and large-scale maintenance more difficult.

  • Predicts missing Python type hints using a GraphCodeBERT-based ML pipeline.
  • Generates deterministic patches without modifying application logic.
  • Designed for local execution and GitHub Actions CI workflows.
Python GraphCodeBERT Machine Learning GitHub Actions Developer Tools

EchoID

Local Voice Speaker Recognition

Identifying speakers accurately with limited training data remains a practical challenge for lightweight voice recognition systems.

  • Developed a CNN-based speaker recognition model using Mel spectrogram features.
  • Improved robustness through waveform and spectrogram augmentation techniques.
  • Supports real-time local inference with a desktop application interface.
Python TensorFlow Keras CNN Audio ML

Selected Work / Engineering Experience

Experience
earned by building

2026 – Present

Independent ML Engineer

Remote · Self-directed build phase

  • Building local-first AI developer tools including Ziv and TypePatch.
  • Focused on semantic search, code intelligence, and applied ML systems.

2025 – 2026

Applied Machine Learning

Self-driven execution

  • Developed ML projects spanning speaker recognition, semantic search, and model deployment.
  • Strengthened Python, deep learning, and software engineering through end-to-end implementations.

2022 – 2025

Programming Foundations

  • Followed a direction-based, mentor-light learning model: weekly topics, self-sourced resources, and self-driven practice.
  • Built a portfolio website and deepened core Python skills through repeated implementation work.
  • Began learning machine learning fundamentals through toy projects, experimentation, and concept-first study.

Engineering Philosophy

Practical Systems

Build software that solves real engineering problems rather than isolated technical demonstrations.

Local-First by Design

Prefer efficient, private, and offline-capable systems that minimize unnecessary cloud dependencies.

Learn Through Building

Turn unfamiliar technologies into production-ready projects through deliberate implementation and iteration.

Contact

Work with me on
something concrete

I’m currently open to ML/AI engineering roles focused on practical systems, local-first products, and semantic search. If your team is building useful infrastructure or has an interesting contribution in mind, I’d be glad to hear from you.

Based in

Kerala, India

Availability

Open to remote and relocation

Send a Message

Prefer email? muhd.uwais51@gmail.com