AI Engineer with 1+ years in GenAI & 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
AI Engineer with 1 + year hands-on experience across the full GenAI stack - including agentic application development, LLM fine-tuning, RAG pipeline design, and production model deployment. Proficient in PyTorch, LangChain, Hugging Face, and LLM APIs (OpenAI, Claude, OllamaComfortable working across research, development, and deployment phases, with a focus on building reliable, scalable AI systems that deliver measurable impact.
Datamites Global Institute
Certification · Data Scientist & AI
N/A – June 30, 2025
Bansal Institute of Science & Technology
B.Tech · Electronics & Communication Engineering
N/A – Present
Trinity Mobility
Associate AI Engineer
January 1, 2026 – Present
Bengaluru, Karnataka, India
Rubixe AI
AI Intern
April 1, 2025 – September 1, 2025
Bengaluru, Karnataka, India
AI Research Assistant Agent
January 1, 2026 – Present
Built a Retrieval-Augmented Generation (RAG) AI agent capable of answering domain-specific queries using custom document knowledge bases with semantic vector search via FAISS; deployed as a production REST API using FastAPI. Implemented a data engineering pipeline for document ingestion, chunking, and embedding generation using OpenAI embedding models, optimizing retrieval precision for downstream LLM inference. Developed a dynamic tool-calling agent workflow with web search and PDF parser integrations, enabling multi-step reasoning and evidence-grounded responses across complex domain queries.
Autonomous Task Execution Agent
January 1, 2026 – Present
Designed an AI agent leveraging agentic RAG architecture with ChromaDB vector storage to retrieve structured knowledge and autonomously execute real-world tasks through connected APIs (email, weather, database). Implemented memory modules and context tracking to support multi-turn conversations and stateful task execution across complex, long-horizon workflows with minimal human intervention. Built a modular tool-calling framework enabling dynamic decision-making and sequential task orchestration — new tools can be added without modifying core agent logic, significantly reducing integration overhead.
Agentic AI Service
January 1, 2026 – Present
Architected a production-grade multi-agent Critical Incident Management (CIM) framework on n8n, featuring a 5-phase agentic pipeline — Intake & Planning, CIM Processing, Domain Enrichment, Review & Execution, and Closure — handling real-time emergency incidents from Kafka/sensor streams and field responder events. Designed a hierarchical multi-agent orchestration system with a Supervisor Agent coordinating specialized domain agents (Fire, Water, Building, Traffic, EMS/Life Safety, Utility) running in parallel execution — each enriching incident context independently before merging and consolidating outputs downstream. Implemented a RAG-powered Response Plan Reviewer that validates AI-generated incident response plans against a vector knowledge base of standard operating procedures, performing schema checks and flagging deviations before passing approved steps to the Execution Agent. Built a self-correcting review loop with an Execution Reviewer agent that continuously validates executed actions against the original plan, flags discrepancies, and triggers replanning — ensuring operational reliability across complex, multi-step emergency workflows. Developed a modular tool-calling layer comprising 15+ specialized tools across 4 categories — Incident Query, Agent Registry & CIM, Review & Execution, and RAG tools — enabling dynamic tool selection and stateful action tracking integrated with CIM API, Vector DB, and Incident State DB.
View ProjectOracle Certified Gen AI Professional
Oracle University
January 1, 2025 – Present
Certified Data Scientist
IABAC
January 1, 2025 – Present
Cultural Fit Analysis
The candidate's projects demonstrate a strong alignment with an AI Engineer role, focusing on practical applications of GenAI, agentic systems, and RAG. The diversity of projects, from critical incident management to research assistants and autonomous task execution, shows a broad interest and capability within the AI domain. The experience with various LLM providers (OpenAI, Claude, Ollama) and frameworks (LangChain, n8n) indicates a willingness to explore and integrate different technologies, which is beneficial for a dynamic team environment. The certifications further validate a commitment to continuous learning and professional development in AI.
Soft Skills & Operational Fit
The candidate's project descriptions highlight strong problem-solving skills, particularly in designing self-correcting review loops and robust guardrail services. The focus on 'production-grade' systems and 'operational reliability' indicates a strong operational fit. The ability to work across research, development, and deployment phases suggests adaptability and a holistic understanding of the AI lifecycle. The detailed descriptions of multi-agent systems and orchestration imply strong logical reasoning and system-thinking capabilities.