AI Engineer with 1+ years in RAG pipelines, multi-agent orchestration, and GPU-accelerated inference
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 B.Tech CSE student and AI Engineer who ships production-ready systems - not just prototypes. Specialises in RAG pipelines, multi-agent orchestration, GPU-accelerated inference, and LLM SaaS backends. Proven track record of cutting manual effort 80%+, accelerating inference 3x, and delivering measurable business outcomes across 3 organisations.
Quantum University
B.Tech · Computer Science & Engineering
August 1, 2022 – July 1, 2026
D.A.V Public School
Intermediate · Science (PCM)
July 1, 2019 – July 1, 2021
Codevidhya India Pvt. Ltd.
Technical Trainer
April 1, 2026 – Present
Raipur, Chhattisgarh, India
LMS Athena
AI / ML Intern
November 1, 2025 – April 1, 2026
Roorkee, Uttarakhand, India
Ceeras IT Services
Frontend Developer Intern
February 1, 2025 – June 1, 2025
India
Face Verification Authentication System
June 1, 2026 – Present
• Achieved 99.2% identity match accuracy using TensorFlow GPU-accelerated YOLOv8-Face + custom embedding models with <150 ms real-time detection latency.
View ProjectMULTI-AGENT-STUDIO
June 1, 2026 – Present
• Cut multi-step AI task completion time by 80%+ via orchestrated 4-agent pipeline (CaveMan Prompt Optimizer G-Stack Navigator Easy Description) with sequential, parallel, and orchestrated execution modes. • Achieved 0 inter-agent context loss by building custom memory management and context-sharing layer enabling seamless handoff across agents. • Integrated 10+ external APIs and tool-calling capabilities enabling end-to-end research 'planning 'execution 'generation in a single automated workflow. • Reduced manual intervention by 80%+ for recurring multi-step AI tasks through automated workflow routing and agent orchestration.
View ProjectAI Chatbot SaaS Platform
November 1, 2025 – April 1, 2026
• Scaled to 200+ enterprise tenants on GPU-accelerated multi-tenant FastAPI backend with role-based access and isolated vector namespaces per tenant. • Reduced average query response time by 65% by implementing RAG pipeline (LangChain + Pinecone) delivering context-aware answers from custom datasets in <2 seconds. • Improved retrieval precision by 38% through embedding fine-tuning and hybrid dense-sparse search strategy over custom corpora. • Cut infrastructure cost by 40% via optimised GPU resource pooling and async batching across concurrent chatbot deployments. • Reduced deployment setup time from 4 hours to 15 minutes by containerising the full CUDA + Flask + TensorFlow stack in Docker with one-command startup. • Handled 500+ concurrent auth requests via REST API with horizontal scalability and zero single-point-of-failure architecture.
British Airways Data Science Job Simulation
Unknown
June 1, 2026 – Present
Deloitte Australia Technology Job Simulation
Unknown
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project diversity, including professional and personal projects, demonstrates initiative and a passion for AI. Their experience spans various aspects of AI engineering, from core model development to deployment and system scaling. The target role of 'AI Engineer' aligns well with their demonstrated skills and project focus. The candidate has also engaged in hackathons and solved numerous LeetCode problems, indicating a proactive and continuous learning mindset. The lack of a psychometric test score prevents a full assessment of cultural fit aspects like team collaboration.
Soft Skills & Operational Fit
The candidate's project descriptions highlight problem-solving, efficiency improvements, and a results-oriented approach. Their experience as a Technical Trainer suggests good communication and mentoring skills. The ability to work on diverse projects (chatbot, face verification, multi-agent studio) indicates adaptability and a broad interest in AI applications. The psychometric test score is 0, which means there is no data to evaluate logical reasoning, work attitude, stress handling, or team collaboration.