AI Engineer with 2+ years in AI Agents, RAG Systems & Node.js Backend Development
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI Engineer and Backend Developer with 2.5+ years of experience building AI agents, RAG systems, multi-agent workflows, and LLM-powered automation solutions using Google ADK, LangChain, Gemini, OpenAI APIs, and n8n. Strong foundation in Node.js backend engineering with experience developing scalable APIs, database systems, and production-ready applications. Passionate about AI orchestration, agentic workflows, retrieval systems, and deploying intelligent automation for real-world use cases.
Gyanmanjari Institute of Technology
Bachelor of Engineering · Computer Engineering
August 1, 2020 – June 30, 2024
Insomniacs
AI Automation Developer & Node.js Backend Developer
February 1, 2024 – Present
India
Trusted Analysis
June 6, 2026 – Present
Built and deployed a production-ready analysis and automation platform for my current company, actively used by 4+ business clients. Designed and developed scalable backend architecture, automation workflows, and optimized database operations to handle real-time business processing. Improved operational efficiency by nearly 60% through workflow automation, reducing manual analysis and repetitive processing tasks. Integrated Salesforce (SFDC) with custom webhook pipelines enabling 24x7 real-time data listening and automated processing of incoming business events from Salesforce systems. Processing real-time sales call data for 4+ enterprise real estate clients through a scalable 24x7 webhook-driven AI pipeline. Reduced manual sales call QA effort by nearly 65% using GenAI-powered transcription, sentiment analysis, and automated insight generation workflows.
View ProjectGen AI Fundamentals
June 6, 2026 – Present
Built 12+ hands-on Generative AI implementations integrating multiple LLM providers including OpenAI GPT-5, Gemini, Mistral AI, Groq, and HuggingFace models through LangChain. Developed interactive CLI-based AI applications exploring embeddings, structured outputs, prompt engineering, conversational memory, persona-driven agents, and semantic search pipelines. Implemented advanced LangChain workflows using ChatPromptTemplate, PydanticOutputParser, SystemMessage, HumanMessage, and AIMessage-based conversational architectures. Strengthened practical AI engineering and LangChain expertise through real-world experimentation, reducing development learning curve by nearly 70% for advanced GenAI application building.
View ProjectResearch Mind Agents
June 6, 2026 – Present
Built a production-grade autonomous multi-agent research system where specialized AI agents collaboratively search, read, analyze, and generate professional research reports. Designed and orchestrated 4 intelligent agents (Search, Reader, Writer, Critic) using LangChain LCEL pipelines and shared memory architecture for end-to-end research automation. Implemented live web retrieval and intelligent scraping pipelines using Tavily API and BeautifulSoup4, enabling real-time fact-based research beyond LLM knowledge cutoffs. Developed an interactive Streamlit dashboard with live agent telemetry, workflow tracking, and automated quality scoring, improving research workflow efficiency by nearly 70%.
View ProjectRAG System
June 6, 2026 – Present
Developed a Retrieval-Augmented Generation (RAG) system capable of answering contextual questions from PDFs, documents, and external knowledge sources with high retrieval accuracy. Implemented end-to-end RAG pipeline including document loading, chunking, embeddings, vector storage, semantic search, and response generation using LangChain and ChromaDB. Experimented with multiple retrievers and embedding strategies, improving contextual response relevance and retrieval quality by nearly 40%. Built modular ingestion workflows supporting PDFs, TXT files, and website-based content for scalable AI knowledge systems. Implemented advanced MMR-based retrieval techniques and intelligent chunking strategies to reduce redundant responses and improve answer precision.
View ProjectCultural Fit Analysis
The candidate's project portfolio demonstrates a strong interest and hands-on experience in cutting-edge AI technologies, particularly Generative AI and agentic systems, which aligns well with an AI Engineer role. The diversity of projects, from professional automation platforms to personal RAG systems and multi-agent research tools, indicates a proactive and curious individual. The candidate's current role as an 'AI Automation Developer & Node.js Backend Developer' further reinforces a practical, full-stack approach to AI engineering. However, the experience level of 2 years is relatively junior for a 'senior' evaluation, and the breadth of experience outside of AI/Node.js is not extensively detailed, which might impact cultural fit for roles requiring broader system design or leadership experience.
Soft Skills & Operational Fit
The candidate's project descriptions highlight a strong problem-solving aptitude and an ability to translate complex AI concepts into practical, efficiency-improving solutions. The focus on real-world business impact (e.g., 60% operational efficiency improvement, 65% reduction in manual QA) suggests a results-oriented mindset. Experience with multi-agent systems and orchestration indicates an ability to design and manage complex workflows. However, without specific psychometric or English test scores, a detailed assessment of stress handling, team collaboration, and communication clarity in a live setting is not possible.