Sarthak Rastogi

He/Him · Auckland, New Zealand

Sarthak Rastogi

AI engineer building AI agents, RAG systems and ML platforms

LinkedInNewsletterFree AI training for leaders

About

I'm an AI Engineer with 3 years of experience working with RAG and AI agents.

I have two degrees in Data Science, and have done research work on ML in top labs worldwide.

AI agentsRAGMachine learningGenerative AILLM researchSoftware engineeringAWSAzure

Things I've built

  • The central AI platform of an enterprise, where all complex agents in the company are built, bringing in $3M+ of cost saving.
  • An AI agent system at a Microsoft-backed US startup, used by 200,000+ users a year.

Experience

  1. AI & Data Solution Engineer, One New Zealand

    Jun 2026 – Present
    • Architected the core agentic AI platform on AWS AgentCore, with MCP integrations to 6 external services. It underpins agents driving $2.6M+ in business value across 2 quarters.
    • Built centralised gateways so other teams can use the platform's MCPs and agents in a governed, observable way.

  2. Generative AI Engineer, One New Zealand

    Feb 2025 – Jun 2026
    • Built a lineage-extraction algorithm to reverse-engineer logic across 30,000+ legacy SQL scripts on AWS SageMaker, unlocking a $40M data modernisation program.
    • Built and own the flagship customer-facing AI agent on Salesforce Agentforce.

  3. Software Engineer, AI, Space and Time

    Jun 2023 – Jan 2025
    • First AI hire at a $300M US startup. Built a natural-language-to-SQL agent processing 200,000+ queries a year.
    • Co-architected DreamSpace, a multi-agent code-generation system.
    • Delivered a text-to-SQL system on open-source LLMs for a multi-billion-dollar US legal firm, at 95% answer accuracy.

  4. Software Engineer Intern, Space and Time

    Feb 2023 – May 2023
    • Built a RAG-based natural-language-to-SQL system from scratch, reaching 93%+ accuracy within two weeks.

  5. NLP Research Intern, Artificial Intelligence Institute, University of South Carolina

    Sep 2022 – May 2023
    • Combined knowledge-graph retrieval with embedding models to build knowledge-infused embeddings.

  6. ML Intern, Prodigal

    Aug 2022 – Jan 2023
    • Integrated 200+ entity extractors into ProNotes for real-time phone-call processing.

  7. ML Research Intern, Technical University of Munich

    Jun 2022 – Aug 2022
    • Trained transfer-learning models that calibrate low-cost air quality sensors, with an R² above 96%.

Projects

Production-grade Text-to-SQL

The SQL generation agent behind a $300M company's data warehouse, used 200,000+ times in a year.

QualityPrompts AI

Open-source Python library that applies 58 researched prompting techniques automatically. 700+ GitHub stars.

Education

IIT Madras

Programming, Data Science. Full ride for two years.

MRU

Computer Science, Data Science and ML. President's medal, full ride all four years.