Rohit RajAI Consultant · Forward Deployed Engineer

One engineer.
Whole product.

Agents, MCP integrations, and LLM features — built inside your team by the person you actually talk to, and shipped to production with evals proving they work. Every repo below is open to read before you email me.

Book free 30-min callor see what shipped
Products still running
30
Agents you can try
10
Repos you can read
40
Days to first commit
5
AI Consultant · Forward Deployed Engineer

An AI consultant who embeds with your team — and ships to production.

Most companies don't need another AI strategy deck. They need one senior engineer inside their Slack and their repo who finds where AI creates value and builds it — agents, MCP integrations, LLM features — until it runs in production with evals proving it. That is forward deployed engineering, and it is how I work.

  • →AI Consultant · Forward Deployed Engineer — based in Bengaluru, India, working with companies worldwide.
  • →Embedded delivery: your repo, your standups, your infrastructure — from day one.
  • →Agents, MCP servers, and LLM features shipped with evaluation suites, not vibes.
  • →Fractional retainer (2 days/week) or fixed-scope pilot — you own the code and IP throughout.
Book a free 30-min scoping call

All of it is public.

30 products and 10 autonomous agents. Every one has a live URL or an open repo, so nothing here is a case study you have to take my word for.

Products

  1. Open MyFinancialMyFinancialPersonal Financial AdvisorData privacy: 100% on-deviceReact 19Vite 7Tailwind CSS 4LiveCode
  2. Open PropCheckPropCheckAI Property Trust Score for IndiaTrust score: 0–100 in 30sNext.js 14Tailwind CSSFastAPI 0.115LiveCode
  3. Open StellarMINDStellarMINDChat-to-SQL with pgvectorQuery latency p95: <1.2sSpring BootSpring AIPostgreSQLCode
  4. Open MicroItineraryMicroItineraryAI Travel PlannerBuild time: 6 weeksReact 18ViteSpring Boot 3.2.2Code
  5. Open Agent AutopsyAgent AutopsyForensic Debugger for Failed AI Agent RunsFailure signatures: 5 classifiedNext.js 16TypeScriptApp RouterCode
  6. Open tinyvoicetinyvoiceFine-Tune a Model in Your Own Voice in an AfternoonTrain time: ~3 min · no GPUMLXQwen2.5-0.5B (4-bit LoRA)PythonCode
  7. Open snap3dsnap3dOne Photo In, an Editable 3D Model OutInput: 1 photo → 3DClaude Fable 5Three.jsNode.js (zero-dep stdlib)Code
  8. Open Agentic OSAgentic OSForce-Directed Map of a 387-Skill Claude Code SetupSkills mapped: 387 · 34 clustersNext.js 16React 19react-force-graph-2dCode
  9. Open claude-autodevclaude-autodevAutonomous 8-Stage Dev Pipeline for Claude CodePipeline: 8 gated stagesNode.js 22+SQLiteHTTP + SSECode
  10. Open KisanSathiKisanSathiSix AI Farm Experts, Keyless and LocalAgents: 6 specialistsFastAPIPython 3.11Next.js 16Code
  11. Open MarginChefMarginChefAI Agent That Finds a Restaurant's Margin LeaksInput: 4 CSVsPython 3.10+richOllama (qwen3:14b)Code
  12. Open QuorumQuorumDeep-Research Agent Swarm with a Shared GraphRAG BrainSwarm: 4 agent rolesPython 3.12FastAPISSECode
  13. Open RegexForgeRegexForgePlain English to a Regex You Can TrustExport targets: 6 languagesNext.jsReactframer-motionCode
  14. Open SkilletSkilletAny Docs Page Into an Installable Agent SkillInput: docs URL or PDFNext.jsReactOllama (qwen3:14b)Code
  15. Open prompt-oceanprompt-oceanType a Sea, Watch It ExistShader: 7 Gerstner wavesNext.jsTypeScriptThree.jsCode
Every project, in full

Autonomous agents

  1. Open ResolvrResolvrAutonomous Support Resolution Agent$15.1B (2026) → $117.9B (2034)FastAPI (Python)React + ViteOllama + cloud-API fallbackCode
  2. Open LooprLooprSelf-Improving Prompt-Optimization LoopFastest-growing dev-tool category of 2026PythonOllama + cloud-API fallbackGEPA-lite reflective loopCode
  3. Open DispatchrDispatchrAutonomous Home-Services Dispatcher$600B+ US home servicesTypeScriptNext.js API routeTool-calling loopCode
  4. Open ClauseGuardClauseGuardAI Contract Risk Review$10B+ legaltechTypeScriptNext.js API routeRule playbook
  5. Open FinScopeFinScopePortfolio X-Ray (educational)Crores of Indian mutual-fund investorsTypeScriptNext.js API routeDeterministic analysersCode
  6. Open MCPGuardMCPGuardMCP Manifest Security ScannerAI-agent security a breakout 2026 categoryTypeScriptNext.js API routeStatic analysisCode
Run one in the browser

The arguments, written down.

142 engineering notes. These are the ones worth reading before you decide whether to buy a builder tool or hire a person — each one costed, with the tradeoff stated plainly rather than sold.

Build vs hire

  1. Open Founding Engineer Equity 2026Founding Engineer Equity 2026How Much to Negotiate (India)11 min readJun 2026
  2. Open Bolt.new vs Hire Developer 2026Bolt.new vs Hire Developer 2026When AI Builder Hits Limits12 min readMay 2026
  3. Open Cursor AI vs Hire Developer 2026Cursor AI vs Hire Developer 2026When $200 Plan Hurts More13 min readMay 2026
  4. Open v0 by Vercel vs Hiring a Developer in 2026v0 by Vercel vs Hiring a Developer in 2026When Generative UI Hits the Day-30 Wall13 min readMay 2026
  5. Open Devin AI vs Hiring a Developer in 2026Devin AI vs Hiring a Developer in 2026$20/Month Agent or Founding Engineer?10 min readMay 2026
  6. Open Replit Agent vs Hiring a Developer in 2026Replit Agent vs Hiring a Developer in 2026Browser IDE Autonomy or Founding Engineer?11 min readMay 2026
  7. Open Claude Code vs Hiring a Developer in 2026Claude Code vs Hiring a Developer in 2026$20 CLI or $80K Engineer?11 min readMay 2026
  8. Open Founding Engineer vs Lovable in 2026Founding Engineer vs Lovable in 2026When $180K Beats $25/mo11 min readApr 2026
  9. Open Hire a Founding Engineer in IndiaHire a Founding Engineer in IndiaDirect vs Toptal, Arc, Uplers in 202612 min readApr 2026
  10. Open India vs US MVP Developer Cost in 2026India vs US MVP Developer Cost in 2026$18K or $120K for the Same App?11 min readApr 2026
  11. Open What a $15K MVP Actually IncludesWhat a $15K MVP Actually Includesvs. the $50K Agency Quote You Just Got11 min readApr 2026
  12. Open Freelance Developer vs Agency in IndiaFreelance Developer vs Agency in IndiaAn Honest Comparison from the Developer Side15 min readApr 2026
Every note, in full
Process

How a 6-week MVP sprint works

Fixed scope. Daily Slack. First production commit by day 5.

  1. 01
    Week 1

    Discovery & architecture

    • Problem framing call (90 min)
    • Architecture doc + tech stack lock-in
    • Milestone schedule signed
  2. 02
    Week 2

    Core backend & auth

    • Database schema + migrations
    • Auth flow (email / OAuth)
    • First production deploy on day 5
  3. 03
    Week 3

    AI / data layer

    • LLM integration (RAG / agents)
    • Vector store + retrieval pipeline
    • Cost guardrails + token budgeting
  4. 04
    Week 4

    Frontend & UX

    • UI flows + mobile responsive
    • Onboarding + empty states
    • Analytics events wired
  5. 05
    Week 5

    Hardening

    • Load tests + p95 latency budget
    • Observability + alerting (Prometheus + Grafana)
    • Security pass + dependency audit
  6. 06
    Week 6

    Launch

    • Bug bash + UAT
    • Public deploy + DNS cutover
    • Code handover + runbook + docs
Engineering Quality

Reliability & Production Readiness

Observability

Prometheus + Grafana

Production-grade metrics, dashboards, and SLO visibility.

  • RED/USE metrics with custom business KPIs
  • Grafana dashboards for latency, throughput, error rates
  • Alerting and environment-aware scrape configuration
Learn more →

Load Testing

k6

Performance validation for high-throughput, event-driven systems.

  • Scenario-based tests (ramping, soak, constant-arrival-rate)
  • Thresholds on p95/p99 latency and error rates
  • CI-compatible execution and reports
Learn more →

API Contract Testing

Postman + Newman

Repeatable regression and smoke testing for REST APIs.

  • Environment-driven collection execution
  • Newman CLI with HTML/JUnit reports
  • Pipeline-friendly contract validation
Learn more →

Event-Driven Testing

Kafka Simulation

Deterministic testing of Kafka consumers and workflows.

  • Forked Kafka simulation repos for event replay
  • Partitioning and ordering validation
  • Failure, retry, and backpressure testing
Learn more →
Testimonials

What Clients Say

Rohit delivered our MVP in 5 weeks — on budget and ahead of schedule. His architecture decisions saved us from rewriting everything when we scaled.

Arjun Kapoor
Founder, NovaByte Labs
MVP Development

We needed a WhatsApp bot for our clinic chain. Rohit understood the problem immediately and shipped a working solution that our staff could use without training.

Priya Mehta
CTO, MediConnect Health
WhatsApp Bot

What impressed me most was the transparency. GitHub access from day one, weekly demos, no surprises. The React Native app he built is still running with zero issues.

Vikram Desai
Product Manager, FinLeap Technologies
Mobile App
FAQ

Common questions before we start

Why hire a founding engineer for hire in India over a US contractor?

A senior founding engineer for hire in India ships the same production AI MVP at 30–40% of US contractor cost, with full code ownership and daily timezone overlap on Slack/WhatsApp. You get end-to-end execution — backend, frontend, mobile, infra, AI — from one person who has shipped and publicly documented every product listed on this site.

How fast can a founding engineer in India ship my AI MVP?

First production commit on day 5, fully-live MVP at week 6 — fixed scope, fixed timeline, no "agency surprise". Every project on rohitraj.tech follows this 6-week shipping cadence.

What if 6 weeks slips?

Fixed scope means we descope features, not extend timeline. You ship on week 6, even if a few stretch features move to v2. You keep what's working.

Who owns the code?

You. Full repo handover on week 6. MIT license by default; commercial-only if you prefer. All IP transfers on final payment.

Am I locked into your tech stack?

No. I default to Next.js / Spring Boot / Postgres because they're boring and hireable. If your team uses Python / Go / Rails, we ship in your stack.

What about post-launch maintenance?

Two options: (1) clean handoff to your team with full docs and a runbook, or (2) ongoing retainer at a fixed monthly rate. No surprise bills either way.

Are you the only engineer?

Yes. No outsourcing, no rotating contractors. You talk to me on Slack / WhatsApp daily. If I get overcommitted I tell you upfront.

Are you open to long-term collaboration?

Yes. Most work starts as a focused sprint, then can continue as a retainer, advisory role, or deeper technical partnership if the product and team are a strong fit.

NDAs and IP?

Standard mutual NDA before kickoff if you want one. All code IP transfers to you on final payment, signed in the master services agreement.

Still reading? Then you have a build in mind.

Tell me what you are shipping and I will tell you, on the call, whether six weeks is realistic and what I would cut to get there. If it is not a fit I will say so — that is a faster answer than a proposal.

Book a free 30-min callSee how the 6-week sprint runs

You own the code, the IP and the repo from week one · First production commit inside 5 days · Daily Slack or WhatsApp access