AKASH C

ML Engineer

https://www.opentalent.in/akash-c-6487079

ML Engineer with less than a year in AI/ML model deployment

Cochin University of Science and Technology (CUSAT)

Key Strengths

Strong foundational knowledge in Machine Learning algorithms (XGBoost, CatBoost, Random Forest, Gradient Boosting, CNN).
Practical experience in building end-to-end ML pipelines, including data ingestion, feature engineering, hyperparameter tuning, and model deployment.
Demonstrated ability to conduct model benchmarking, evaluation (R²), and residual diagnostics.
Experience with deploying ML models via REST APIs (Flask) and integrating with web/mobile applications.
Proficiency in Python and relevant ML/data science libraries (Keras, TensorFlow, Scikit-Learn, Pandas, NumPy).

AI is analyzing your overall score…

Identifying your key strengths…

Evaluating your skill match against the job requirements…

Assessing your cultural and operational fit

About

ML Engineer with hands-on research experience building and deploying predictive models on a government-funded smart city project (RUSA 2.0) at CUSAT. UGC NET qualified professional seeking an AI/ML engineering role to ship production-ready models. Experienced in delivering full ML pipelines from data cleaning to deployment across various algorithms including XGBoost and CatBoost.

Top Skills

PythonXgboostrandom forestTensorFlowKeras

Education

University of Calicut

MSc · Computer Science

N/A – June 30, 2025

College of Applied Science, Vazhakkad

BSc · Computer Science

N/A – June 30, 2023

Experience

Cochin University of Science and Technology (CUSAT)

Junior Research Fellow

October 1, 2025 – Present

Cochin, Kerala, India

Projects

Smart Policing CNN Crime Classification Engine

June 23, 2026 – Present

Trained a CNN text classifier on crime reports to automate categorization, replacing manual triage processes. Developed a rule-augmented risk scoring module combining model confidence with victim vulnerability features and keyword severity. Deployed the model via a Flask REST API, integrating it with both a web portal and an Android application.

Smart Home - Property & Design Marketplace

June 23, 2026 – Present

Built a multi-stakeholder web platform handling four distinct user roles (homeowners, architects, contractors, vendors) and permission sets. Users can browse pre-defined designs, request custom plans and compare architect budgets.

Certifications

Full Stack Development (MERN)

KASE, Edunet Foundation, and EY

June 1, 2026 – Present

UGC NET Computer Science

NTA

June 1, 2024 – Present

Key Strengths

Strong foundational knowledge in Machine Learning algorithms (XGBoost, CatBoost, Random Forest, Gradient Boosting, CNN).
Practical experience in building end-to-end ML pipelines, including data ingestion, feature engineering, hyperparameter tuning, and model deployment.
Demonstrated ability to conduct model benchmarking, evaluation (R²), and residual diagnostics.
Experience with deploying ML models via REST APIs (Flask) and integrating with web/mobile applications.
Proficiency in Python and relevant ML/data science libraries (Keras, TensorFlow, Scikit-Learn, Pandas, NumPy).

Cultural & Operational Fit

Cultural Fit Analysis

The candidate's experience in a research fellow role at a university and involvement in a government-funded project suggests a preference for structured environments and projects with clear objectives. Their personal projects demonstrate initiative and a breadth of interest beyond core ML, including full-stack development. The 'Smart Policing' project shows an interest in applying ML to real-world societal problems, which aligns with impact-driven organizations. The 'Smart Home' project indicates an ability to handle complex multi-user systems. The candidate's academic background and certifications further support a continuous learning mindset.

Soft Skills & Operational Fit

The candidate demonstrates strong analytical and problem-solving skills through their research fellow role and project work, particularly in optimizing models and identifying key drivers. Their focus on reproducible experiments suggests an organized and detail-oriented approach. The ability to work on government-funded projects implies adherence to structured processes and documentation. Collaboration is implied through project work involving multiple stakeholders and integration with different applications.