Full Stack Engineer with 4+ years in agentic AI systems and LLM-powered applications.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Results-driven Full Stack Developer and AI Engineer with deep expertise in building production-grade agentic AI systems, LLM-powered applications, and automated workflows. Specializes in designing multi-agent architectures using LangGraph, CrewAI, and AutoGen - orchestrating autonomous pipelines that reason, plan, and execute complex tasks end-to-end. Proficient in the full development stack from React/Next.js frontends to FastAPI/Node.js backends, with strong command over LLM integration, RAG pipelines, vector databases, and AI task automation. Passionate about shipping real-world AI products that bridge cutting-edge research with scalable engineering.
Indira Gandhi National Open University (IGNOU)
Bachelor of Computer Applications (BCA)
June 1, 2022 – December 1, 2025
Autonomous Multi-Agent Research & Task System
June 17, 2026 – Present
Architected a multi-agent system using LangGraph and CrewAI with specialized agents for research, synthesis, code generation, and report writing — operating autonomously end-to-end. Implemented persistent agent memory, tool-use (web search, code execution, file I/O), and dynamic task planning using OpenAI function calling and custom tool registries. Integrated LangGraph state machines to manage complex multi-step workflows with conditional branching, retry logic, and human-in-the-loop checkpoints. Deployed via FastAPI with a React frontend dashboard showing real-time agent activity, token usage, and task progress.
RAG-Powered Knowledge Engine with Hybrid Search
June 17, 2026 – Present
Engineered an end-to-end RAG pipeline combining dense vector retrieval (FAISS / Pinecone) with BM25 sparse search for hybrid retrieval — improving answer relevance by 40%+. Implemented advanced chunking strategies (semantic chunking, sliding window), metadata filtering, and re-ranking with cross-encoder models to reduce hallucinations. Built a modular LLM backend supporting hot-swap between OpenAI GPT-40, Claude, and local Hugging Face models without code changes. Exposed as a production REST API via FastAPI with streaming responses, rate limiting, and async processing.
AI Workflow Automation Platform
June 17, 2026 – Present
Built AI-powered automation workflows using n8n and Make.com, integrating LLM nodes for dynamic content generation, classification, and routing within business pipelines. Developed custom webhook-driven agents that monitor triggers (email, Slack, calendar), process inputs via Claude/GPT APIs, and execute multi-step automated actions. Created Python-based automation scripts bridging no-code platforms with custom AI logic — enabling non-engineers to deploy LLM workflows through a simple UI. Reduced manual operational tasks by 70%+ through intelligent AI automation of document processing, report generation, and CRM data enrichment.
Full Stack SaaS E-Commerce Platform
June 17, 2026 – Present
Built a production-grade SaaS platform with Next.js 14 (App Router), TypeScript, and Tailwind CSS frontend, backed by a Node.js/Express API and PostgreSQL database. Implemented Firebase Auth for multi-provider authentication (Google, Email), Stripe payment integration, and real-time cart/inventory management with Redis caching. Designed a RESTful API with JWT-protected routes, role-based access control, and webhook handlers for payment events — deployed on AWS EC2 with GitHub Actions CI/CD.
LLM Fine-Tuning Pipeline (SLM Specialization)
June 17, 2026 – Present
Fine-tuned Mistral-7B and LLAMA-3 variants using LoRA/QLORA on domain-specific instruction datasets via Hugging Face PEFT and TRL libraries. Built evaluation harnesses measuring ROUGE, BERTScore, and task-specific accuracy metrics; tracked all experiments with MLFlow. Optimized inference with quantization (GPTQ/GGUF) and served models via a custom FastAPI endpoint with streaming token generation.
Algorithmic Trading Automation System
June 17, 2026 – Present
Developed Pine Script multi-timeframe trading indicators with automated signal generation, SL/TP risk management, and backtesting — directly paralleling AI experiment-cycle thinking. Explored integrating ML-based price prediction signals with rule-based execution logic — bridging statistical modeling with automated decision systems.
Cultural Fit Analysis
The candidate demonstrates a strong cultural fit for roles requiring innovation and a blend of full-stack development with advanced AI/ML capabilities. The diverse range of projects, from multi-agent systems and RAG pipelines to full-stack e-commerce and algorithmic trading, showcases a broad interest and ability to tackle varied technical challenges. The focus on building autonomous systems and automating workflows aligns well with forward-thinking, agile environments. The candidate's self-identified 'Rapid Learner' strength further supports adaptability, which is crucial in fast-evolving tech landscapes. However, the lack of traditional work experience makes it difficult to assess collaboration within a team setting.
Soft Skills & Operational Fit
The candidate's project descriptions highlight a results-driven approach and a passion for shipping real-world AI products. The emphasis on reducing manual operational tasks by 70%+ through AI automation suggests a strong focus on efficiency and practical problem-solving. The ability to adapt quickly to new frameworks and turn research papers into working prototypes indicates a proactive and agile operational fit. However, without specific psychometric or English test scores, a comprehensive assessment of communication clarity, work attitude, stress handling, and team collaboration is limited.