Quality Engineering track

Quality Engineering Intern

Flocci Chat · product team

chat.flocci.in
Part-time InternshipRemote (India)2 months~20 hrs/week1 opening
Applications close
30 September 2026
Cohort
Next cohort begins October 2026
What you get
Certificate + merit bonus
How the two months run

What is the Quality Engineering Intern position on Flocci Chat?

A part-time, two-month on-job training position testing Flocci Chat, our embeddable AI support widget. Roughly 20 hours a week alongside your semester. You test grounding — whether an answer really came from the customer’s content — plus embedding across host sites, streaming behaviour and escalation, then own a surface after the gate.

The role

What this posting actually is

Flocci Chat is a support widget a business embeds on its own site. It reads that business’s website and knowledge base first, so its answers should be grounded in their real content rather than in whatever the model happens to believe. The single most important question about this product is therefore a testing question: when it answers, did the answer actually come from the customer’s content, or did it come from nowhere?

That makes for unusually interesting quality work. You will ask it things its knowledge base cannot possibly answer and record what it does — refuse, hedge, escalate, or confidently invent. You will feed it a knowledge base that contradicts itself and see which side it picks. You will interrupt a streaming answer halfway, embed the widget in a page whose CSS fights it, open it on a mid-range Android phone on a weak connection, and ask it something in Hindi.

This posting is part-time by design, roughly 20 hours a week, so it fits alongside a running semester. Same two months, same gate, same certificate. Clearing the gate means you move from charters we write to a surface you own — you design the evaluation set, you decide what "the answer was grounded" means operationally, and you fix small defects yourself.

The product team

The product you would join: Flocci Chat

Flocci Chat is a white-label AI support widget you embed on your own site; it grounds answers in your website and knowledge base and can take real actions for a customer.

Read the full Flocci Chat page

How the two months run

Testing first. Then a gate. Then the codebase.

Nobody is handed the codebase on day one, on any track. This is the arc for this posting specifically — the phases, the gate in week four, and what you produce in each.

  1. Phase 1Weeks 1–3

    Application testing on an answer you cannot predict

    You get a staging Chat instance with a seeded knowledge base and the requirement notes for grounding, escalation and the embed. You start from charters we give you and quickly move to designing your own probes. The discipline is recording everything — the exact prompt, the exact answer, the expected source — because with an AI product a report without the transcript is worthless.

    What you produce

    • An evaluation set of at least forty questions spanning answerable, unanswerable and contradicted cases, with the observed behaviour recorded for each.
    • Grounding defect reports: answers that could not have come from the knowledge base, with the full transcript attached.
    • An embed report covering at least three host pages with different CSS and one mobile viewport.
    • A written list of the non-functional requirements a support widget carries — first-token latency, bundle weight, behaviour on a dropped connection — and what you measured.

  2. The gate — not everyone passes

    Phase 2Week 4

    The gate — explain how an answer is produced

    You walk an engineer through the path of one question: the widget, the gateway, the retrieval over the customer’s content, the call to the Intelligence service, the streamed response, and the credit metered against it. You classify your defects functional or non-functional, and you say how you would prove the product got better after a change rather than just different.

    What you produce

    • An end-to-end account of a single question, from the widget to the metered AI call and back.
    • Your defects classified, with the requirement each violates named — including the ones you argue are non-functional.
    • A written proposal for how a grounding change should be evaluated before it ships.
    • The track decision for month two: own a surface, or continue on structured charters with supervision.
  3. Phase 3Weeks 5–8

    Own the evaluation surface

    Your evaluation set becomes the thing the team runs before a change to the answering path goes out. You maintain it, you extend it to Hindi and mixed-language queries, and you fix the small defects you filed — usually on the widget side, in reviewed pull requests. Interns who did not clear the gate continue on structured charters with supervision and finish with the same certificate.

    What you produce

    • An owned evaluation set the team runs before shipping changes to the answering path.
    • A regression list for the embed and streaming behaviours.
    • Merged fixes for small defects you found, reviewed by the engineer who owns Chat.
    • A written closing review of your two months.

The work

What you will actually do

  • Build and run an adversarial question set against a seeded knowledge base — questions it can answer, questions it cannot, questions whose answers are contradicted in two places — and record exactly what the widget does with each.
  • Verify grounding rather than assuming it: for each answer, trace which source it should have come from, and file the ones that came from nowhere.
  • Test escalation — when the widget should stop trying and hand over to a human, and whether the handover carries the conversation with it.
  • Test the widget as an embedded guest on somebody else’s page: colliding CSS, a strict content security policy, a cramped mobile viewport, a page that is already slow.
  • Test streaming behaviour under real conditions — a dropped connection halfway through an answer, a tab backgrounded mid-stream, a question sent twice in a second.
  • Check the agentic actions: when the widget does something for a customer rather than just replying, confirm it does it exactly once and reports it honestly when it fails.
  • Watch the non-functional side: time to first token, widget bundle weight on a slow connection, and whether a retried request meters credits twice.

Who this is for

What you need, and what simply helps

Requirements

  • You are in your 2nd, 3rd or 4th year of an engineering degree and can commit roughly 20 hours a week for two continuous months.
  • A schedule you can actually keep alongside classes, agreed in writing before you start. Part-time is not "when I get time".
  • You are comfortable in browser DevTools and willing to read a network request and a streamed response.
  • You can write a defect report about an AI answer precisely — including what you asked, what it said, and what it should have said instead.
  • Enough scepticism to not be impressed by a fluent answer. Fluency is not correctness, and that instinct is the job.

Nice to have

  • You have used ChatGPT, Gemini or a similar assistant enough to have caught one confidently making something up.
  • You have embedded a third-party script or widget on a page and seen it break the layout.
  • Basic HTML and CSS — enough to understand why a host page’s styles can leak into a widget.
  • You can read JSON responses without needing them formatted for you.
  • Comfort testing in a second Indian language — Hindi coverage genuinely matters on this product.

The stack

What you would be working with

  • The embeddable Flocci Chat widget and its host-page integration
  • Browser DevTools — network, console, throttling, device emulation
  • The Flocci Intelligence service behind the answers (DeepSeek via the OpenAI SDK)
  • Postman or curl against the chat API, including streamed responses
  • Read-only psql against the staging PostgreSQL database for conversation and metering records
  • A written evaluation set you build and maintain yourself
  • The issue tracker and the release checklist the team actually uses

What you leave with

What you will learn that college does not teach

  • How to test a system whose output is not deterministic — where "it gave a different answer" is not automatically a defect and you need a real evaluation method.
  • What grounding means in practice, and how to prove an answer came from a source instead of taking the model’s word for it.
  • How embedded third-party widgets fail on other people’s websites, which is a whole category of bug most students never meet.
  • Non-functional testing that actually matters on Indian networks: time to first token, payload weight, behaviour on a flaky connection.
  • How metering works — and why an idempotency bug in an AI product is a billing bug, not just an engineering one.

Eligibility

Before you apply, check these

  • Enrolled in a full-time engineering programme at an Indian institution (B.E./B.Tech/M.Tech or an equivalent diploma).
  • Available for roughly 20 hours a week across two continuous months, on a fixed agreed schedule.
  • Remote from anywhere in India, with a connection stable enough for a weekly video call.
  • Your own laptop, and ideally a phone you can test the widget on.
  • If this is a college-mandated OJT, your institution must accept an unpaid, part-time, remote industrial-training placement — check this before applying, since some colleges require full-time hours.

Selection

How we decide

Five steps, in this order. The written answers carry more weight than the resume.

  1. Apply with your resume, a GitHub or any link to work you have done, and the two written answers below.
  2. A 20-minute screening call, including agreeing the weekly schedule that will fit around your classes.
  3. A practical exercise: we give you a small knowledge base and a chat transcript, and ask you to mark which answers were grounded in it and which were not.
  4. A conversation with the engineer who owns Chat about your exercise and the two months.
  5. Offer and joining letter, with the college paperwork attached.

Compensation

Certificate + merit bonus

A certificate of completion for every intern who finishes the programme.

Interns whose work clears an exceptional bar are considered for a completion bonus at the end of the two months. It is earned, not scheduled.

This is an unpaid industrial-training position

The programme

What we provide, and what we expect back

Identical on every posting — this is one programme with several tracks.

What we provide

  • A real product, not a sandbox: a live Flocci surface with real customers, its requirement notes, and a staging environment of your own to break.
  • A certificate of completion for every intern who finishes the two months, on either track.
  • Code review from the engineers who own the service — on your commits, and on your defect reports before that.
  • Access to the tooling that matters: the repositories, staging environments, the issue tracker, and read access to the databases you are testing against.
  • A weekly one-to-one where you are told plainly how you are doing, including when it is not going well.
  • A written closing review, and consideration for a completion bonus if your work clears an exceptional bar.

What we expect

  • Roughly 40 hours a week on the full-time track and roughly 20 on the part-time track, on a schedule agreed in writing before you start.
  • A daily written update: what you did, what you found, what is blocking you. Three lines is enough. Silence is not.
  • Defect reports another person can follow without asking you a single question.
  • That you use the product properly before you judge it, and read the requirement before you call something a bug.
  • Confidentiality. You will see customer data structures and unreleased work; it stays inside.
  • Honesty about what you do not know. It is the single fastest thing you can do for yourself here.

The bar

  • Show up. Two months is eight weeks and eight weeks is short. If you cannot make a day, say so before it starts, not after it has passed.
  • Reproduce it before you report it. A bug you saw once and cannot make happen again is a note to yourself, not a defect report.
  • Read first, then ask. The requirement, the existing code and the error message answer most questions. Ask once you have read all three and it still does not make sense — then ask immediately, not on Friday.
  • Do not ship code you cannot explain. If you cannot say why a line is there, it does not go in. Pasting a fix you do not understand is worse than saying you are stuck.
  • Write in plain sentences. Half of this work is being understood — in a defect report, a commit message, a stand-up note. Nobody here is impressed by long words.

For colleges

If this is your college's on-job training requirement

  • We issue the paperwork colleges normally ask for: a joining letter at the start of the two months and a completion certificate at the end, stating the dates, the track, the product worked on and the weekly hours.
  • Attendance and progress are recorded weekly. A college mentor or TPO can be named on the application — they will receive the joining confirmation, a mid-programme note and the completion certificate, and can write to us directly at workshop@flocci.in. If your institution needs a periodic report or a signed logbook in its own format, tell us in the application and we will keep our records in that shape.
  • The part-time track exists for exactly this situation: if your training window runs alongside a semester, send us your college schedule and the two months are structured around it.
  • What we will not do: promise a placement, backdate a certificate, or certify hours that were not worked. These are unpaid industrial-training positions — if your college requires a paid placement for the training to count, please check that before you apply.

The company

About Flocci Technologies

Flocci Technologies is an India-based, AI-native software company founded in 2023 and built in Ranchi, Jharkhand. It publishes a connected estate of software: 20 product surfaces — audience engagement, AI support, recruiting, sales, meetings, work apps — plus 8 full ERP and POS systems for hotels, schools, garages, libraries, marts, pharmacies and restaurants. It is priced in rupees, billed through PayU, and designed around how Indian businesses actually operate rather than translated from a US product.

The idea holding it together is called One Flocci: every product runs on the same shared layer instead of reinventing it. Identity handles sign-in, organisations, teams and roles once, for everything. Payments holds a single credit wallet you top up once and spend in any product. Intelligence is the shared, metered AI layer every app calls, so AI behaves and bills the same way everywhere. Graph is the cross-app event spine, carrying counts and metadata but never your content. Notifications is one delivery pipe for transactional email and one-time codes, and Gateway is the only public door in — it resolves the app, verifies the session and strips untrusted identity headers before anything reaches a service.

Flocci was founded by MD Afsar Hussain, who spent 10+ years as a senior engineer at SAP Labs India across S/4HANA, ABAP, Fiori and BTP before building this platform. He studied at BIT Mesra (B.Tech) and BITS Pilani (M.Tech), mentors 30+ startups and runs AI and coding workshops across India. That enterprise background shows up in how the estate is built — shared services, auditable rails, systems meant to survive being depended on — and it is why an internship here is run as engineering rather than as a workshop.

What that means for you as an intern: you will touch production code and production data structures used by real customers, not a training sandbox built for interns. The product you are assigned is live while you are testing it. When your commit merges, it gets deployed and somebody uses it. That is the appeal and it is also the reason for the gate in week four — real code carries real consequences, so we make sure you understand the system before you change it.

The facts

Company
Flocci Technologies — an India-based, AI-native software company
Founded
2023
Headquarters
Ranchi, Jharkhand, India
Founder
MD Afsar Hussain, Founder & CEO — 10+ years as a senior engineer at SAP Labs India
Scale
20 product surfaces and 8 ERP/POS systems on one shared platform
Platform
One account, one credit wallet and one AI layer across every product
Contact
workshop@flocci.in

The stack, across the estate

Frontend
Vite + React + TypeScript single-page apps, Tailwind and shadcn components
Backend
Node.js and Express services, with some Python/FastAPI
Database
PostgreSQL
Realtime
Socket.io — Flocci content features are realtime by default
AI
DeepSeek through the OpenAI SDK behind a provider abstraction, or through the shared Intelligence service
Payments
PayU, metered per action against one credit wallet
Infrastructure
Self-hosted OVHcloud VPS with nginx and pm2; sibling -ui and -srv repositories per product, conventional commits

Questions

Questions about this posting

Apply for the Quality Engineering Intern position on Flocci Chat

1 opening · Remote (India) · Next cohort begins October 2026. Applications close 30 September 2026.

Elsewhere in the cohort

Other open roles

Quality EngineeringQuality Engineering InternFlocci Hotels Suite · Ranchi, Jharkhand (Hybrid)View roleEngineeringSoftware Engineering InternFlocci Pulse · Ranchi, Jharkhand (Hybrid)View roleEngineeringSoftware Engineering InternFlocci Talent Suite · Remote (India)View role
See all 8 postings and how the programme works

Quality Engineering Intern

Flocci Chat · closes 30 September 2026