Data Scientist

HiroJet; Mumbai; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

HiroJet is seeking a data science expert to own end-to-end credit and fraud data science for its STPL product in Mumbai. You will build and deploy scorecards, engineer features from bureau data and alt-data, and partner with product and engineering to bring rules live.

You will debate with founders using evidence and drive improvements in risk and fraud controls. The role requires 5+ years in data science, hands-on digital lending experience, and a track record of production-grade models and

Qualifications

• 5+ years overall experience in data science/analytics.
• Digital lending: minimum 3 years hands-on in digital lending/consumer credit.
• Built and deployed at least one credit scorecard into a live BRE/LOS.
• Parsed and engineered features from raw bureau files (CRIF / CIBIL / Experian JSON/XML).
• Experience with repeat-borrower ladder / limit-management policies.
• Worked with SMS/alt-data/device signals for underwriting or fraud.
• Able to write production-quality notebooks and scripts.

Responsibilities

• Build and maintain credit scorecards and models for FTB and Repeat Borrowers (XGBoost, RF, SVM, ensembles).
• Engineer features from raw bureau JSON and alt-data sources.
• Design, validate, and ship models with clear trade-offs.
• Own portfolio risk analytics and monitoring.
• Build fraud signals and priortise fraud backlog into production.
• Collaborate with engineering to productionise features and models.
• Refine tier/ladder policy with evidence and communicate with founders.

Skills

Data science

Analytics

Credit scoring

Model deployment

Bureau data

Alt-data

Python

SQL

XGBoost

Random Forest

SVM

Tools

XGBoost

Random Forest

SVM

Job description

Mandatory: 2–3 years of experience working on Short-Term Personal Loan (STPL) products

About the company

We are a listed NBFC (BSE & NSE) with ~40 years of history. Alongside a co-lending / fintech partner book, we run -our own B2C short-term personal loan (STPL) product launched in late 2025. Ticket sizes are ₹1,000–₹15,000, and tenures are 3–6 months. We are a team (~35–40 people) operating like a startup inside a regulated public listed NBFC.

The Role

Own end-to-end credit & fraud data science : feature engineering from raw bureau JSON ,SMS,DEVICE, scorecard / model development, Business Rule Engine (BRE) design, monitoring, and partnering with product/engineering to put rules live. You will work directly with the existing DS team, tech, product and founders — decisions are data-backed and debated.

What you will own

• Build and maintain credit scorecards and models for FTB and Repeat Borrowers (Xgboost, Random forest, Support Vector Machine Models, ensemble models, challenger models).
• Engineer features from raw CRIF (or equivalent) bureau JSON — tradelines, enquiries, DPD histories, identity matches — and from raw SMS / FinBox alt-data (collections, rejections, salary, app footprint).
• Design, validate, and ship Models: hard rejects, soft flags, amount caps — with clear lift/capture / approval trade-offs.
• Own portfolio risk analytics: vintage / DPD / non-starter / POS bad-rate monitoring; propose tier pauses, cool-offs, and ladder-up changes.
• Build fraud signals (device, SIM/OTP, mule, ring, post-disbursal disappearance) and help prioritise the fraud PRD backlog into production.
• Partner with engineering to productionise features, rules, and models (Watchtower-style shadow
• Challenge and refine existing tier/ladder policy with evidence; communicate clearly to founders and business.

Required experience

• Tenure: 5+ years overall experience in data science/analytics.
• Digital lending: Minimum 3 years hands-on in digital lending/consumer credit (NBFC, fintech lender, digital/STPL) who has built models themselves.
• Scorecards/models: Built and deployed at least one credit scorecard (first-time borrower or repeat borrower, or combined model) into a live BRE / LOS. Should improve approval–bad-rate trade-offs from production experience.
• Bureau: Parsed and engineered features from raw bureau files (CRIF / CIBIL / Experian JSON or XML) — not only vendor-precomputed attributes.
• Limit Assignment: Experience with repeat-borrower ladder / limit-management policies.
• Monitoring and QC: Shadow underwriting/champion–challenger frameworks.
• Alt-data: Worked with SMS / alt-data / device / AA signals for underwriting or fraud (FinBox, similar vendors, or in-house SMS parsing). statsmodels). Able to write production-quality notebooks and scripts, not just slide decks.
• Communication: Comfortable debating policy with founders/credit heads using data; owns the "show me the evidence" conversation.

Nice to have

• Prior Experience: Prior work at a zero-to-one digital lender or STPL product.

What success looks like in 6 months

• A documented feature dictionary from raw bureau + SMS with IV/KS ranking.
• At least one new scorecard/model live with clear expected vs observed bad-rate impact.
• Non-starter / First Payment Defaults monitoring with actionable rule recommendations and clear demonstrated improvements in defaults
• Credible pushback on weak policy ideas — backed by analysis, not opinion.

Hiring process

• Screening call and technical deep dive (role fit, digital lending depth).