Anom Chakravorty Dithered
anom_

Founding AI Engineer · Miivo

I build AI agents and take them all the way to production: orchestration, retrieval, durable workflows, guardrails and evals. I love building products with taste, where the engineering and the design get the same care.

  • Open to AI Engineer · Full-stack AI · Founding · FDE roles
  • 7× hackathon winner
  • India · remote
How I ship agents Projects GitHub LinkedIn

Focus

Four tracks that feed each other. Use the arrows, or wait.

01 / 04

Agentic systems

Agents that plan, call tools and finish the job. A model in a loop with MCP tools, retrieval and memory, built so a bad step is caught and retried instead of shipped.

  • Tool calling
  • MCP
  • RAG
  • Multi-agent
02 / 04

Durable workflows

Agents fail halfway through things. I run them as durable workflows: every step checkpointed, retried and resumable, with guardrails and evals in the path.

  • Inngest
  • Workflow SDK
  • Guardrails
  • Evals
03 / 04

Forward-deployed delivery

Start from the customer's process, not the model. Scope it with the people who do the work, prototype in days, then wire the agent into their stack. At Miivo that is AI automation for businesses across the UAE.

  • Discovery
  • Prototyping
  • Integrations
  • Handover
04 / 04

Design to production

I design with Claude Design and Figma, then build with Impeccable in the loop, so the interface is typeset, laid out and audited before it ships. What comes out is production-ready UI on real tokens and components.

  • Claude Design
  • Figma
  • Impeccable
  • shadcn/ui
  • Tailwind CSS

Work

Five years, from an internship to founding engineer.

  1. NOW
    Sep 2024 – present
    Dubai, UAE · remote

    Founding AI Engineer

    Miivo
    • Architected and built the platform end to end in a TypeScript monorepo using Next.js, Bun, Hono, PostgreSQL and GCP, spanning product architecture, APIs, data models, background pipelines and production systems.
    • Built the AI Sales Agent and lead-generation workflows for prospect discovery, qualification and personalized outreach, powered by LLM/RAG pipelines and context-aware automation.
    • Designed the metrics engine and opportunity-generation system, and integrated QuickBooks and Xero financial data to unify P&L, cash flow, margins and operational signals into actionable business insights.
    • TypeScript
    • Next.js
    • Bun
    • Hono
    • PostgreSQL
    • GCP
    • LLM / RAG
  2. Nov 2023 – Aug 2024
    Gurgaon, IN

    Full Stack Developer Intern

    Bitscale
    • Built core product workflows for an AI-powered GTM data platform, enabling teams to source and enrich leads, run AI-driven company research, surface intent signals and automate personalized outbound workflows across CRM and sales tools.
    • Next.js
    • TypeScript
    • Go
    • LLMs
    • Postgres
  3. Aug 2022 – Mar 2024
    Bengaluru, IN

    Full Stack Development Teaching Assistant

    Crio.Do
    • Enhanced the proficiency of over 1000 professionals and students in software development, achieving 95% SLA compliance through mentorship, comprehensive explanations and problem-solving.
    • MongoDB
    • Express
    • React
    • Node.js
  4. Aug 2021 – Aug 2022
    India · freelance

    Technical Content Writer

    GeeksforGeeks

    Published technical articles and tutorials on web development. Read the articles.

  5. Jan 2022
    San Francisco · remote

    Software Engineer Intern

    Anakin (YC S21)
    • Automated data extraction and scraping from e-commerce sites for a YC-backed startup.
    • Maintained the data warehouse and the team's reporting in Google Data Studio.
    • Web scraping
    • Data extraction
    • Data warehousing
    • Google Data Studio

Day to day

How I use AI at work: Claude, skills and plugins, as a shell session. Pick a command, or let it run.

anom@agents: ~/day

anom@agents:~$ claude /grill-me

  • Most work starts in Claude: I talk the problem through before any code.
  • Sometimes with Matt Pocock's skills: /grill-me to stress-test the idea, /to-spec to write it down.
  • The spec's acceptance criteria become the first eval set.

anom@agents:~$ claude /implement

  • /to-tickets splits the spec. Claude Code builds each ticket, tests first.
  • Several sessions run in parallel branches. I read every diff.
  • MCP servers hand them the repo, the docs and the schema.

anom@agents:~$ ls ~/.claude

  • Anything I explain twice becomes a Skill: instructions Claude loads when the task calls for them.
  • Plugins bundle skills, commands and MCP servers, so every machine gets the same setup.
  • Impeccable is the one I reach for when the task is UI.

anom@agents:~$ claude /code-review

  • /code-review checks the diff against the spec and the standards.
  • No prompt or model change ships without the eval suite.
  • When something breaks: /diagnosing-bugs, a failing test first, then the fix.

anom@agents:~$ deploy --durable

  • Long-running agents run as durable workflows: checkpoint, retry, resume.
  • A person approves the steps that can hurt.
  • I read real traces. Every failure becomes a new eval.

Projects

Five things I built and shipped, most of them in a weekend. Each one is live. Tilt the sheets.

Storz

Web3 file storage and sharing. Files are pinned to IPFS and shared by link, with no central server holding them.

GitHub115 stars · 66 forks
Built withJavaScript · IPFS
RecognitionDecentralized Storage Infrastructure Award, Web3 Infinity 2022 (Filecoin)

Lern

A platform to learn anything, with lessons generated by Google's PaLM 2.

RecognitionGrand Prize, Atlas Madness 2023 (Google & MongoDB)

Codz

A coding platform with a GPT-3.5 assistant beside the editor.

Built withJavaScript · GPT-3.5

Hackathons

Prizes from 2021 to 2023, solo and with teams. Tilt a badge to move its light, click to flip it.

Weekend builds · collector's set

  • Atlas MadnessGrand PrizeGoogle & MongoDB · Team Lern
  • Web3 InfinityDecentralized Storage Infrastructure AwardFilecoin · Team Storz
  • IEM HacksGrand PrizeTeam Optimisers
  • Pasckathon 3.0Grand PrizeTeam Optimizers
  • Razorpay FTX2nd Grand PrizeTeam Rixtox
  • Appwrite × Dev.toRunner-upSolo
  • Ureckathon1st runner-upTeam Optimisers
  • GeeksforGeeks GPL3rd PrizeSolo

Agent stack

End to end, in the order it happens: from a customer's problem to an agent running in production.

01 · ScopeWith the customer: map the workflow and agree what done looks like.
  • Discovery
  • Process mapping
  • Success metrics
  • Eval set first
  • Rapid prototypes
02 · OrchestrateThe agent loop and the tools it can call.
  • Vercel AI SDK
  • Claude Agent SDK
  • Google ADK
  • LangChain
  • CrewAI
  • Pi agent harness
  • MCP
  • Tool calling
  • Multi-agent
03 · GroundPut the right context in front of the model.
  • RAG
  • Embeddings
  • Pinecone
  • Vector databases
  • Hybrid search
  • Context engineering
04 · Make durableSurvive crashes, timeouts and half-finished runs.
  • Inngest
  • Workflow SDK
  • Durable workflows
  • Queues & retries
  • Idempotency
  • Human-in-the-loop
05 · GuardLimit what goes in, what comes out and what it may do.
  • Guardrails
  • Structured outputs
  • Prompt-injection defence
  • PII redaction
  • Approval gates
06 · EvaluateMeasure it before and after every change.
  • Evals
  • Testing frameworks
  • Benchmarking
  • LLM-as-judge
  • Regression suites
07 · Deploy & observeShip it, watch it, feed failures back to stage 06.
  • GCP
  • AWS
  • Vercel
  • Docker
  • Serverless
  • CI/CD
  • Observability
  • Tracing
  • Cost & latency budgets

Underneath all of it

Languages & runtime
  • TypeScript
  • JavaScript
  • Python
  • Go
  • Node.js
  • Bun
  • Hono
Frontend & product
  • Next.js
  • React
  • shadcn/ui
  • AI Elements
  • Tailwind CSS
Data & tooling
  • PostgreSQL
  • MongoDB
  • MySQL
  • Git

Let'stalk.

Hiring an AI Engineer, a full-stack AI engineer, a founding engineer or a Forward Deployed Engineer? I am open to all four. Email is the fastest way to reach me.

anomchakravorty3008@gmail.com