HARIKA GOPISHETTI

AI Engineer

https://talent.gravityer.com/harika-gopishetti

AI Engineer with less than a year in Machine Learning, LLM-based Applications & Backend Development.

Google Cloud

Key Strengths

Strong foundational knowledge in Machine Learning and AI, demonstrated through academic projects.
Practical experience with LLM-based applications, specifically RAG, including prompt engineering and vector databases (FAISS).
Proficiency in Python and relevant ML/AI libraries (Numpy, Pandas, scikit-learn, LangChain).
Experience in developing end-to-end ML pipelines, from data preprocessing to model evaluation and deployment (Tkinter GUI).
Exposure to backend development concepts (REST APIs, Node.js, Express.js) which is valuable for deploying AI solutions.
Understanding of model evaluation metrics and techniques for classification tasks.

Cultural & Operational Fit

Cultural Fit Analysis

The candidate's academic background in Computer Science Engineering (AI & ML) and project work align well with an AI Engineer role. The diversity of projects, from traditional ML classification to modern RAG-based LLM applications, shows a breadth of interest within AI. The Google Cloud internship, even if virtual, indicates an interest in industry-standard tools and cloud environments. However, the lack of professional experience beyond virtual internships means the candidate's adaptability to a corporate culture and collaborative work environment is yet to be proven.

Soft Skills & Operational Fit

The candidate demonstrates a proactive learning attitude through academic projects and virtual internships. The project descriptions indicate an ability to work on complex technical problems and deliver functional solutions. The focus on user-friendly interfaces (Tkinter GUI) suggests an awareness of end-user needs. However, without direct interview data, specific soft skills like teamwork, problem-solving under pressure, or communication in a professional setting cannot be fully assessed.

AI is analyzing your overall score…

Identifying your key strengths…

Evaluating your skill match against the job requirements…

Assessing your cultural and operational fit

Projects

AI Knowledge Assistant using RAG

July 1, 2025 – June 1, 2026

Developed an AI-powered knowledge assistant capable of answering user queries from custom documents using Retrieval-Augmented Generation (RAG). Built a document ingestion pipeline to process PDFs and text files, generate embeddings, and store them in a FAISS vector database for semantic retrieval. Implemented prompt engineering techniques to improve response relevance and reduce hallucinations during LLM inference. Integrated REST APIs for query processing and retrieval workflows, enabling scalable backend communication. Evaluated retrieval quality and response accuracy through testing and optimization of chunking and embedding strategies. Utilized Python, LangChain, FAISS, and Large Language Models to create an end-to-end conversational AI application.

Thyroid Detection Using Machine Learning

January 1, 2025 – December 31, 2025

Built and benchmarked an end-to-end supervised ML classification pipeline across 3 algorithms (Random Forest, SVM, Naive Bayes) on a 6,962-record clinical dataset, with Random Forest achieving 99% accuracy. Applied SMOTE oversampling to address class imbalance, improving model generalization across hypothyroid, hyperthyroid, and euthyroid categories. Engineered and normalized 8+ clinical features (TSH, T3, T4, TT4, age, gender) using StandardScaler and LabelEncoder to standardize inputs and improve model performance. Evaluated models using accuracy, precision, recall, F1-score, and confusion matrices for interpretable healthcare prediction analysis. Developed a Tkinter-based GUI enabling dataset uploads, model training, and real-time disease prediction for non-technical users.

View Project

Key Strengths

Strong foundational knowledge in Machine Learning and AI, demonstrated through academic projects.
Practical experience with LLM-based applications, specifically RAG, including prompt engineering and vector databases (FAISS).
Proficiency in Python and relevant ML/AI libraries (Numpy, Pandas, scikit-learn, LangChain).
Experience in developing end-to-end ML pipelines, from data preprocessing to model evaluation and deployment (Tkinter GUI).
Exposure to backend development concepts (REST APIs, Node.js, Express.js) which is valuable for deploying AI solutions.
Understanding of model evaluation metrics and techniques for classification tasks.

Cultural & Operational Fit

Cultural Fit Analysis

Soft Skills & Operational Fit

HARIKA GOPISHETTI

Key Strengths

Cultural & Operational Fit

About

Top Skills

Skills

Education

Experience

Projects

Certifications

Key Strengths

Cultural & Operational Fit