Skip to content
vbVatsalya Betala

Experience

Things I’ve worked on in the real world

Most of my industry work has involved a similar translation problem:

take something technically possible and turn it into something another person can actually use.

  1. Apr 2026 – Present

    Skai Lama

    AI Chief of Staff Intern

    At Skai Lama, I’ve been working less on isolated AI features and more on the connective tissue around them.

    One project was a Universal Context Bot that lets the team query information spread across Notion, Slack, Trello, and Google Drive through a single natural-language interface using Claude Projects and MCP servers.

    I also built an AI content workflow around n8n and Claude that collects signals from internal tools, turns them into research briefs, and helps produce drafts. That cut manual content-research time by roughly 70%.

    Other work has included Slack-based systems for extracting standup intelligence, generating sprint checklists, surfacing action items, and producing team digests.

    ClaudeMCPn8nAgentsAutomationRAG / Context Systems
    Side quest: the n8n content engine

  2. May 2025 – Jul 2025

    Addverb

    AI Optimization Intern

    Warehouses are a good reminder that optimization becomes much more interesting once physical constraints enter the picture.

    At Addverb, I built an LLM-powered SQL interface so warehouse managers could ask operational questions in natural language rather than manually querying databases.

    I also worked with Warehouse Execution System logs to investigate routing and decanting strategies, with proposed changes showing an 8–12% improvement in simulated pick efficiency.

    A separate set of experiments looked at AutoStore-inspired coordination strategies and scheduling heuristics for reducing robot congestion under high load.

    Some of the tested scheduling heuristics reduced simulated robot congestion by approximately 15% under high-load conditions.

    OptimizationLLMsSQLWarehouse SystemsSchedulingSimulation

  3. Dec 2024 – Mar 2025

    LLMate

    Machine Learning Engineer Intern

    At LLMate, I worked on an NLP-driven marketing analytics system that combined more than 150,000 rows of data from Facebook Ads, Shopify, and Google Analytics.

    The goal was to make that data explorable through natural language rather than another dashboard full of filters.

    I worked on fine-tuning, retrieval-augmented generation, prompt chaining, and retrieval logic, including changes that improved latency by roughly 20–25% on common analytics queries.

    NLPRAGLLM Fine-tuningAnalyticsRetrieval

  4. Dec 2023 – Jun 2024

    Ques.AI

    Delhi, India · Hybrid

    AI Engineer Intern

    A lot of the work here was around turning raw media into something actually usable.

    I worked with OpenAI Whisper and Google Cloud NLP to build podcast features around transcription, sentiment analysis, and hashtag generation.

    I also built API-driven workflows for generating Instagram posts using GPT-based content generation and the Meta Graph API.

    It was one of my earlier experiences seeing how much of an AI product is really the plumbing around the model: APIs, orchestration, formatting, and getting outputs into the place where someone can actually use them.

    OpenAI WhisperGoogle Cloud NLPMeta Graph APIREST APIsGPT

  5. May 2022 – Jul 2022

    Voiro Technologies

    Data Science & Product Intern

    This was one of my earliest chances to see how modeling choices connect to business decisions.

    I worked on lead scoring using XGBoost and PCA, and on automating advertising-inventory workflows.

    The lead-scoring work improved sales-opportunity identification by 45%, while workflow automation reduced manual processing effort by roughly 30–35%.

    XGBoostPCAData ScienceAutomation

Education