Full Stack Engineer with less than a year in Semantic Search and DSA.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Final Year Computer Science with experience building scalable full-stack and ML-backed applications using FastAPI, React, and modern backend architectures. Strong foundations in software engineering, REST APIs, databases, distributed systems concepts and performance optimization. Built end-to-end projects involing semantic search, vector indexing, and real-time retrieval systems with focus on stability, system design, and engineering reliability. Strong problem solving skills with 1200+ DSA problems solved (Leetode - Knight, CodeForces - Specialist).
University of Petroleum and Energy Studies (UPES)
Bachelor of Technology - B.Tech · Computer Science
August 1, 2022 – June 1, 2026
SenseCluster
June 1, 2026 – Present
Built a full-stack semantic deduplication platform using FastAPI and React to prevent redundant question submissions using embedding similarity. Designed REST APIs for embedding generation, similarity ranking, and conditional storage of novel queries with PostgreSQL integration. Implemented vector-based retrieval pipelines to return semantically related questions and answers, improving knowledge reuse and reducing duplicate data growth. Developed responsive frontend workflows for real-time duplicate detection and immediate user feedback. Performed API testing, debugging, and end-to-end validation to ensure reliable backend and retrieval system behavior.
View ProjectHallucinateGPT
June 1, 2026 – Present
Engineered a high-performance semantic search system in C++ implementing HNSW, KD-Tree, and brute-force nearest neighbor search with support for multiple distance metrics. Developed RESTful backend services and an interactive frontend dashboard to visualize high-dimensional embeddings using PCA and benchmark retrieval latency across indexing algorithms. Implemented a Retrieval-Augmented Generation (RAG) pipeline using local LLM integration via Ollama, enabling semantic document retrieval and context-aware response generation. Optimized retrieval scalability by engineering a multi-layer HNSW graph index for approximate nearest-neighbor search, inspired by architectures used in modern vector databases such as Pinecone and Milvus. Performed performance benchmarking and debugging across retrieval pipelines to evaluate latency, indexing efficiency, and search accuracy.
View ProjectCultural Fit Analysis
The candidate's academic projects demonstrate a strong interest in cutting-edge technologies like LLMs, vector databases, and semantic search, aligning with an innovative and growth-oriented culture. The breadth of technologies used (C++, Python, JavaScript, React) and competitive programming achievements suggest a driven and continuous learning mindset. The focus on building complete, functional systems from scratch indicates a strong sense of ownership and initiative, which would generally fit well within a product-focused engineering team.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a proactive approach to problem-solving and a focus on end-to-end system development. The emphasis on performance optimization, debugging, and testing suggests an operational mindset. However, without direct interview data, specific soft skills like teamwork, leadership, or adaptability cannot be fully assessed.