Python Developer & AI/LLM Systems

Kugelblitz Private Limited; Rajasthan; Híbrido; INR 350.000 - 700.000; Jornada completa

Descripción de la vacante

Keka Inc. is seeking a fresher Python Developer to join our Data Engineering team in Jaipur for building data pre-processing pipelines and AI-ready data for lending fintech workflows.

You will work on ETL/ELT scripting, document intelligence, and collaboration with backend engineers to understand loan data models while gaining exposure to ML/AI basics and production pipelines.

Formación

• B.Tech/B.E. in Computer Science, IT, Data Science, or related field (2025/2026 graduates preferred)
• Strong academic or personal project portfolio demonstrating Python + data work
• No prior professional experience required — we'll train on our domain (lending, accounting, regulatory data handling)
• Exposure to fintech, credit scoring, or document processing is a plus

Responsabilidades

• Data pre-processing pipelines — cleaning, normalizing, validating structured and semi-structured fintech data for AI use
• LLM/AI project support — building data pipelines for prompt pipelines, RAG systems, embeddings
• ETL/ELT scripting — Python jobs moving data between LOS/LMS databases, data warehouse, and AI services
• Document intelligence — pre-processing scanned KYC documents, bank statements, and agreements (OCR cleanup, embeddings)
• Data quality & validation — building checks to catch inconsistencies before they reach financial or AI systems
• Collaboration with backend teams — understand loan/accounting data models before designing pipelines

Conocimientos

Python

Pandas

NumPy

SQL

REST APIs

Git

ML basics

Problem solving

Educación

B.Tech/B.E. in CS/IT/Data Science

Herramientas

Docker

LangChain/LlamaIndex

OpenAI API

AWS basics

Descripción del empleo

Location: Jaipur, Rajasthan, India (On-site/Hybrid)

Experience: 0–1 years (Freshers welcome)

Employment Type: Full-Time

Function: Software Developer / Applied AI

About the Role

We build enterprise-grade lending infrastructure — Loan Origination, Loan Management, Collections, Co-Lending, and Financial Accounting systems — used by NBFCs, MFIs, HFCs, and BNPL providers. As we extend this platform with AI-driven automation , we're looking for a fresher Python Developer to join our Data Engineering team.

This is a hands-on role focused on preparing, cleaning, and structuring financial data (loan, KYC, repayment, collections, transaction data) so it can reliably feed ML models, LLM pipelines, and RAG/AI applications. You'll work at the intersection of data engineering and applied AI — not pure research, but production pipelines that touch real money movement and regulated data.

What You'll Work On

• Data pre-processing pipelines — cleaning, normalizing, and validating structured (loan schedules, ledgers) and semi-structured (KYC docs, agent notes, SMS/call transcripts) fintech data for downstream AI use
• LLM/AI project support — building data pipelines that feed prompt pipelines, RAG systems, and embedding generation for use cases like loan document summarization, collections call analysis, and underwriting assistance
• ETL/ELT scripting — writing Python jobs to move data between our LOS/LMS databases, data warehouse, and AI services
• Document intelligence — pre-processing scanned KYC documents, bank statements, and agreements (OCR output cleanup, chunking for embeddings, PII masking)
• Data quality & validation — building checks to catch inconsistencies before they reach financial or AI systems (a bad row in a repayment dataset breaks both reconciliation and model output)
• Collaboration with backend teams — working alongside Java/Spring Boot engineers to understand loan/accounting data models (Fineract-style entities: loans, clients, transactions, GL accounts) before designing pipelines around them

Must-Have Skills

• Solid fundamentals in Python (data structures, OOP basics, writing clean/testable scripts)
• Working knowledge of Pandas / NumPy for data manipulation
• Basic SQL — joins, aggregations, filtering on relational data
• Understanding of REST APIs (consuming and integrating with them)
• Familiarity with Git and version control workflows
• Conceptual understanding of ML/AI basics — what embeddings, vector search, and LLM prompting are, even without production experience
• Strong problem-solving ability and attention to detail (critical when working with financial data — a silent data error here has downstream accounting impact)

Good-to-Have (Not Mandatory for Freshers)

• Exposure to LangChain / LlamaIndex, OpenAI/Anthropic APIs, or vector databases (Pinecone, Weaviate, pgvector)
• Academic/project experience with NLP (tokenization, text classification, NER)
• Familiarity with Docker basics
• Exposure to AWS (S3, basic ECS/Lambda concepts)
• Any personal/academic project involving fintech, credit scoring, or document processing
• Basic understanding of Java/Spring Boot (useful since our core platform is Fineract-inspired, though not required day one)

Qualifications

• B.Tech/B.E. in Computer Science, IT, Data Science, or related field (2025/2026 graduates preferred)
• Strong academic or personal project portfolio (GitHub link expected) demonstrating Python + data work
• No prior professional experience required — we'll train on our domain (lending, accounting, regulatory data handling)

Why This Role Is Different From a Generic "Python Fresher" Job

• You'll work with real regulated financial data (loan lifecycles, repayments, KYC) — not toy datasets — so you'll learn data quality discipline that matters (auditability, correctness, PII handling under India's DPDP Act)
• Direct exposure to how AI is being applied inside core lending workflows, not just chatbots — underwriting support, collections prioritization, document automation
• Mentorship from engineers working on a Fineract-style, multi-tenant, API-first platform at scale

What We Offer

• Structured onboarding into both the fintech domain (loans, accounting, collections) and our AI tooling stack
• Exposure across the full stack: data engineering AI pipelines production integration with LOS/LMS
• Growth path into ML Engineering, Data Engineering, or AI Platform roles