Skip to content

Adhikram Maitra

I sit in the workflow. Then I ship the agent that has to survive it.

Most mornings I am still on a New York broker's screen, working remote from India. At I am founding engineer on the commercial real-estate dashboard they close on. RAG over 20K+ financial documents, a chat they can stay in for the whole deal, outreach that lifted qualified deal flow about 10x, and more than $100K through a loop the desk can run after I leave the chair.

The product I operate in public is . Job intel plus a tailoring workbench for people who already live in an editor. 400+ company trails, an MCP that Cursor and Claude can call, Chrome capture, LaTeX resumes. About 2,000 unique people use it on a given day.

Two other products sit outside that job. is in my hands now. A free nutrition and strength app for a household, Expo on both phones, no paywall. was the seller-ops SaaS I took from a blank repo to $20K+ MRR, with 30K+ listings enriched so outreach had something true to send.

I learned to trust a pipeline the long way. Four years on 's ad-tech data plane at Directi. Kafka at 50k records a second, Spark jobs that compared nearly 3 billion rows in 30 minutes, streaming audits that cut latency about in half. Before that, . A community backend that reached 10K users in three months while notifications held at 2K messages a day.

I want the next seat that still starts in someone else's workflow. Sit with the operator, ship agents and RAG against live systems, leave a number they can keep moving. Looking forward to forward-deployment opportunities.

GitHubLinkedInTwitter

Work

Experience

Products

GripGrams, TechPrufer, Equal Collective. Click a car to open it on the right.

How I work

Same loop at ANAX, TechPrufer, Equal Collective, and GripGrams. Sit in the seat, then leave a number.

  1. 01

    Sit in the seat

    Brokers, sellers, job seekers. I work from their screen, not a backlog they never open.

  2. 02

    Name the number

    Deal flow, latency, MRR, applications sent. If it does not move, it is not the job.

  3. 03

    Ship on their stack

    Next.js, Python, MCP, Spark: whatever they already run. Agents and RAG only where they pay rent.

  4. 04

    Leave the loop

    MCP, evals, docs. The next person should ship faster than I did on day one.

Then back to the seat.

Stacks I actually use

Agents, languages, backend, cloud, data, analytics, systems — plus the mobile kit for GripGrams.

AI & agents

Agentic AIAgent OrchestrationRAGMCPGeminiHarnessAgent EvalMulti-LLM IntegrationLLM Fine-TuningVector DatabasesCursorClaude Code

Languages

TypeScriptPythonJavaScriptSQLScalaJavaRubyC++

Backend & frameworks

Next.jsNode.jsPostgreSQLDrizzleExpressREST APIsRuby on RailsMicroservicesAstro

Cloud & DevOps

AWSDockerRedisSQSGitNginxJenkinsEC2EMRAzure

Data engineering

SparkKafkaHiveStructured StreamingPySparkHDFSETLData ModelingMySQL

Analytics

MetabaseA/B TestingData PipelinesReal-time AnalyticsPerformance Monitoring

Systems

System ArchitectureDistributed SystemsDesign PatternsOOPAlgorithms

Mobile

ExpoReact NativeFirebaseLinuxpm2 / VPS

GitHub

2,100 contributions in the last year

View on GitHub
Learn how we count contributions
@Anax-Codex@indi-codex@Intellish-Inc

Open source

Forks I use in production. Also on Adhikram.

Reading

Feature trails I follow on TechPrufer.

  1. Cloudflare

    Artificial Intelligence Integration & Impact

    Open trail on TechPrufer →

am. my initials. sit in the seat, then ship.