AI Engineer with less than a year in Generative AI & Machine Learning.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AIML engineering graduate driven to take models from the notebook to production. I specialize in architecting end to end Generative AI pipelines, focusing heavily on multi agent workflows, two stage RAG, and Graph Neural Networks (PyG). Leveraging Python, vector databases, and analytics tools, I transform complex, unstructured data into scalable, real-time business intelligence.
Nitte Meenakshi Institute of Technology
Bachelor of Engineering · Artificial Intelligence and Machine Learning
November 1, 2022 – June 1, 2026
Aqmenz Automation Pvt Ltd
AIML Intern
March 1, 2024 – April 1, 2024
India
Medical Literature Intelligence System using RAG, LlamaIndex and Qdrant
June 24, 2026 – Present
Developed a citation-grounded Medical RAG system that ingests PubMed papers via the Entrez API, transforms abstracts into BGE-M3 embeddings, and enables evidence-backed medical question answering with PMID-level traceability. Engineered a two-stage retrieval pipeline combining Qdrant vector search and BGE Cross-Encoder reranking, implementing metadata filtering and contradiction-aware synthesis to improve retrieval precision and reduce hallucinations. Built a production-ready Streamlit application leveraging LlamaIndex CitationQueryEngine and Groq-hosted LLMs to generate real-time, source-cited responses from medical literature while enforcing factual grounding and safety constraints.
Cyber Risk Prediction using GNN (Final Year Project)
June 24, 2026 – Present
Built a graph-based intrusion detection system using GraphSAGE (PyTorch Geometric) on 300K+ network flows from CIC-IDS2017 and UNSW-NB15, leveraging graph topology to capture relational attack patterns for threat prediction. Engineered a scalable preprocessing pipeline handling class imbalance correction, feature engineering, and standardization across 300K+ records, ensuring consistent, production-ready inputs for deep learning workflows. Designed a k-NN graph structure (k=5) and optimized a GraphSAGE model over 100 epochs with Adam, achieving 100% recall, validated through confusion matrices and per-class performance analysis.
Agentic Product Manager using LangGraph (Streamlit)
June 24, 2026 – Present
I developed an Agentic AI Product Management platform using Python, LangGraph, Streamlit, and OpenAI APIs. It transforms high-level product ideas into structured requirements, strategy plans, technical architectures, and sprint roadmaps. A multi-agent workflow employs specialized Requirement, Strategy, Architecture, Validation, and Sprint Planning agents. Autonomous validation loops refine outputs before generating PRD Documentation and Sprint Planning documents. This reduced product planning effort by automatically generating 50+ requirements, architecture decisions, and sprint deliverables. It delivers downloadable documentation and execution plans through an interactive web interface.
Cultural Fit Analysis
The candidate's projects demonstrate a strong interest and alignment with the target role of an AI Engineer, particularly in cutting-edge areas like Generative AI, RAG, and GNNs. The diversity of projects (product management, medical intelligence, cyber security) indicates a broad intellectual curiosity and adaptability, which are positive indicators for cultural fit in a dynamic AI environment. The academic background in AI/ML further reinforces this alignment. However, the limited professional experience (one short internship) means there's less data to assess long-term team collaboration and adaptability within a corporate culture.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a proactive and problem-solving mindset, with a focus on practical application and measurable outcomes (e.g., 'reduced product planning effort by automatically generating 50+ requirements'). The academic project on Cyber Risk Prediction also highlights attention to detail in data preprocessing and model optimization. The internship experience, though brief, shows an ability to deliver a complete system with a dashboard, suggesting good operational awareness. However, without direct interaction or psychometric test results, a deeper assessment of stress handling, teamwork, and communication clarity in a professional setting is limited.