The dive Download PDF

AI Engineer · Mumbai

Tanish Shah

Engineer with a founder's bias. At 20, I run a live AI sales and growth stack for a global fintech-education company (voice agents, LLM email, AI content), owned from build to audit to cost.

Experience

AI Intern, Marketing Automation & Growth

QuantInsti Quantitative Learning Pvt. Ltd., Mumbai

Jul 2026 to present

Make · LeadSquared CRM · OpenAI · Retell AI · Twilio · Vobiz · Claude Code

  1. Outbound voice agents

    • I own the Retell AI outbound calling agents on Twilio and Vobiz telephony.
    • I added social-engineering guardrails to 28 live agent prompts.
    • I fixed a silent failure in the 24-hour call-frequency guard.
    • I built timezone-aware regional routing and a callback scheduler, and expanded calling coverage from 9 to 59 countries.
    • I built a daily call-funnel report.
  2. AI email engine, live on real leads

    • A two-stage LLM pipeline (strategist, then writer) that writes one persona-targeted nurture email per CRM lead webhook, at about $0.33 per email.
    • It ships through audit-driven releases.
    • I designed its core rule: a lead's personal data steers the message but never appears in it.
  3. Content engine

    Playwright · ffmpeg · AI voice

    • AI short-form reels produced through a code pipeline.
    • "The Desk" reached 2,300 views in under 48 hours against a 555-view account median. It became the account's best reel and now its reference format.
    • Designed from a 44-reel baseline and a 25-account study.
    • I also run an AI-assisted X replies programme and WhatsApp bulk campaigns.
  4. Cost and reliability

    • When the org hit its 300k-credit automation cap, I attributed spend per module and ranked the savings.
    • I built a gate that stops malformed LLM output from reaching the CRM.
    • I flagged security issues in live automation configs.

Backend Automation Engineer Intern (sole technical hire)

AMAFHH Import and Export Pvt. Ltd., Mumbai

Jun 2025 to Sep 2025

FastAPI · Windows Server · Tally · Google Sheets

  • Owned the architecture, build and deployment of a production backend (HTTPS, IP allowlisting, HMAC-SHA256 request auth).
  • Built a voucher pipeline from Google Sheets through FastAPI and XML into Tally, handling godown logic, conditional GST rules and a ±1% broker tolerance. It eliminated fulfilment errors on real transaction volume.
  • Brought back in Oct 2026 to build a multi-user delivery-challan web app (per-user login, GST calculation, print preview, challan history).

Projects

  1. InferenceLens

    Python · PyTorch · FastAPI · WebSocket · MPS

    • An open-source GPU-layer profiler for self-hosted LLMs. It covers the gap between LangSmith and NVIDIA Nsight, because neither shows per-layer GPU attribution.
    • GPT-2 on Apple unified memory shows 33% p50 to p99 jitter. Llama 3.1 8B on a dedicated NVIDIA GPU, a model 64x larger, shows 7.8%.
    • It located 4x layer-level attention bottlenecks.
  2. Agentic Futures Trading Engine

    Groq · Llama 3.1 8B · Docker

    github.com/RedPillCoder1/trading-bot
    • Turns natural-language trade intent into Binance Futures orders.
    • A zero-trust validation layer blocks hallucinated parameters before any network call.
    • Result: zero invalid exchange requests in paper-trading tests.
  3. Autonomous Venture Lab

    FastAPI · Next.js · LLM agents · Monte Carlo

    autonomousventurelab.vercel.app
    • An AI startup-investment analyst.
    • A 4-agent LLM team (CEO, CFO, CMO, Critic) with schema-enforced JSON handoffs debates each venture.
    • Then 10,000 Monte Carlo simulations per request across 4 exit scenarios return a probabilistic verdict in under a second.
  4. 4-agent software team

    CrewAI · OpenAI Agents SDK

    • PM, Developer, Tester and Reviewer agents that turn a feature spec into tested, reviewed code.
  5. Voice Agent Call QA Auditor

    CrewAI

    github.com/RedPillCoder1/voice-agent-call-qa-auditor
    • A CrewAI multi-agent system that audits voice-agent calls, built on synthetic call data.

Education

D. J. Sanghvi College of Engineering

B.E. Computer Engineering, Minor in Data Science

CGPA 9.11/10 · Graduating Jun 2027

NPTEL Top 1% nationally, Python for Data Science

Skills

AI & Agents
LLM pipelines, prompt engineering, multi-agent systems, guardrails, OpenAI Agents SDK, CrewAI, RAG
Voice & Telephony
Retell AI, Twilio, Vobiz, ElevenLabs, HeyGen
Automation & GTM
Make, Zapier, LeadSquared CRM, webhooks, WhatsApp, outbound email, short-form video
Engineering
Python, JavaScript, SQL, FastAPI, Node.js, Next.js, PyTorch, Docker, Git, Claude Code daily