Tanishq Yadav
Software Developer
Pune
Summary
Focused AI/ML and Full-Stack Developer with hands-on experience building end-to-end ML pipelines, RAG-based systems, LLM-integrated products, and scalable web applications. Proficient in Python, PyTorch, Scikit-learn, Pandas, FastAPI, and modern web technologies for developing and deploying production-ready solutions. Experienced in prompt engineering, semantic search, vector databases, REST APIs, and creating intuitive user interfaces backed by robust backend systems. Strong collaborator with backend and product teams—I don't just experiment, I ship impactful AI and web products from concept to deployment.
Overview
3
3
Certifications
1
1
year of professional experience
Work History
Associate L1 – Generative AI Intern
Infotact Solutions
Remote
06.2026 - Current
- Developed Generative AI applications using LLMs, RAG, and Prompt Engineering.
- Built AI solutions with Python, LangChain, Hugging Face, and OpenAI APIs.
- Integrated AI models with APIs and backend systems for production-ready applications.
- Collaborated in agile teams and contributed to code reviews and live projects.
Full Stack Development Intern
Sysslan IT Solutions
Remote
06.2026 - 07.2026
- End-to-End Development: Engineered a full-stack Event Feedback Management System, managing the entire lifecycle from initial frontend interface design to final functional testing.
- Full-Stack Integration: Established seamless communication between the frontend and backend by building robust API routes and implementing necessary form validation to ensure data integrity.
- Database Management: Developed fundamental database operations, including creating collections and implementing CRUD functionality to efficiently store and retrieve user feedback data.
Machine Learning Intern
Jyesta Corporate
Remote
07.2025 - 09.2025
Data Engineering: Conducted comprehensive data cleaning, preprocessing, and Exploratory Data Analysis (EDA) on large datasets using Python (Pandas, NumPy) to ensure model readiness.
Algorithm Implementation: Built and optimized clustering models using K-Means for customer segmentation, improving targeting accuracy and identifying key user personas.
Model Evaluation: Applied statistical techniques and performance metrics (Accuracy, Precision, F1-score) using Scikit-learn to validate and refine predictive models.
Education
Bachelor of Technology - Computer Science and Engineering
01-2028
- Focus: DSA, Algorithms, Web Technologies, Mathematical Modeling
- Meta Front-End Developer Certified
- GPA: 9.3 / 10.0
Skills
Languages & Core CS: Python (Advanced), C, C, SQL DSA, OOPs, DBMS, Operating Systems, Computer Networks
Backend & Web: Nodejs, FastAPI, REST APIs, System Design basics HTML5, CSS3, JavaScript (ES6), JSON
AI/ML & Tools: Prompt Engineering, LLM Evaluation (Gemini, Claude, ChatGPT), Hallucination Detection Git/GitHub, Docker, Redis, SQLite
Accomplishments
- Research Publication: Built and published a concurrent Node.js API gateway for 5G mMTC backend systems (Zenodo, 2025) — validated at 250K+ requests/30s with zero packet loss.
- Google Student Ambassador — selected to represent Google's developer ecosystem across student tech communities.
Timeline
Associate L1 – Generative AI Intern - Infotact Solutions
06.2026 - Current
Full Stack Development Intern - Sysslan IT Solutions
06.2026 - 07.2026
Machine Learning Intern - Jyesta Corporate
07.2025 - 09.2025
Pimpri Chinchwad University - Bachelor of Technology, Computer Science and Engineering
Projects
RAG-based Resume Analyzer & Job Fit Scorer | Python, sentence-transformers, ChromaDB, Mistral, FastAPI, Streamlit (https://resumeiq-analyser.streamlit.app) Developed ResumeIQ, an AI-powered resume screening tool that analyzes resume–job description alignment, generating fit scores, skill extraction, missing keywords, and actionable improvement recommendations. Built a RAG-based matching pipeline using PDF text extraction, chunking, local embeddings, ChromaDB vector storage, semantic search, and Groq-hosted Llama 3.3 70B for structured resume analysis. Engineered a full-stack solution with FastAPI backend and Streamlit frontend, deployed on Render and Streamlit Cloud for a cost-efficient, serverless workflow
DocuChat (https://docuchatlangbot.streamlit.app) • Built a PDF-based Q&A system using LangChain, HuggingFace Embeddings, FAISS, and Groq Llama 3.3 70B to enable natural language querying of documents. • Implemented an end-to-end RAG (Retrieval-Augmented Generation) pipeline with text chunking, vector search, and LCEL-based retrieval chains for accurate document question answering. • Developed and deployed a single-file Streamlit application on Streamlit Cloud, eliminating the need for a separate backend while maintaining full document processing and inference capabilities.