Data Engineer - Climate Fintech

Catalysk isn’t just another startup — it’s a paradigm shift. We’re building the world’s first Sustainability Score for Individuals — like a credit score, but for your climate footprint. By converting electricity, water, commute, and spending data into an actionable rating, we’re creating the foundation for green finance, insurance, and incentives. At population scale.

You’ll be part of an early-stage team where your work is visible, impactful, and globally relevant.

About the Role

We’re looking for a hands-on Data Scientist / ML Engineer to build the data and API layer that powers Catalysk’s financial intelligence.

Catalysk works with large volumes of bank, card and UPI transaction data. Much of this data is messy, inconsistent and unstructured. Your primary responsibility will be to build the data pipelines and services that turn this raw data into clean, structured and usable information for our ML, merchant categorisation and analytics teams.

You will work closely with our existing teams across merchant categorisation, machine learning and analytics, contributing directly where your data, NLP or ML expertise is useful.

Key Responsibilities

Data Engineering — Core Responsibility

• Build and maintain ETL/data pipelines for bank, card, UPI and other financial transaction data.
• Clean, transform and standardise raw financial data into structured, reusable datasets.
• Work with different data formats and sources and integrate new datasets into Catalysk's data platform.
• Build data-quality checks, validation processes and monitoring for important datasets.
• Develop reusable features and data transformations for ML, merchant categorisation and analytics.
• Investigate data issues and inconsistencies and build robust solutions rather than one-off fixes.

APIs & ML Enablement — Core Responsibility

• Build APIs/services that expose data-processing and ML/NLP workflows to other parts of the Catalysk system.
• Define clear input/output schemas and structured responses.
• Take workflows from notebooks/prototypes into testable, reusable services.
• Build lightweight testing and evaluation frameworks for these services.
• Work with engineering and DevOps to make these services available in UAT and live testing environments.

Performance, Optimisation & Scalability — Core Responsibility

• Profile data pipelines, APIs and model-inference workflows to identify performance bottlenecks and unnecessary processing.
• Optimise Python code, SQL queries, data transformations and processing workflows for speed, memory usage and cost.
• Improve the latency and throughput of APIs and data-processing services.
• Design efficient approaches for processing large transaction datasets without unnecessary recomputation and Identify optimisation techniques where appropriate.
• Establish basic performance benchmarks and monitor improvements as the system evolves.
• Help ensure that prototypes and data workflows can scale from testing to production-level transaction volumes.

Merchant Categorisation & NLP — Significant Responsibility

• Work with the merchant categorisation team to improve transaction narration understanding.
• Build and evaluate BERT/transformer-based models for merchant/entity extraction and classification.
• Prepare training and evaluation datasets.
• Analyse classification errors and improve the underlying data, features or models.
• Experiment with LLMs where they are useful for transaction understanding.
• Help improve merchant mappings, aliases and transaction intelligence.

Support for ML & Analytics

• Support the ML team with dataset preparation, feature engineering and exploratory analysis.
• Help investigate model performance and data-related issues.
• Support the analytics team with reliable datasets and ad-hoc analysis when required.
• Explore new transaction signals and datasets that could improve Catalysk's models and intelligence.

Who We're Looking For

• 3–5 years of hands-on experience in data engineering, ML engineering, data science
• Strong Python and SQL skills.
• Strong experience with data pipelines, ETL/ELT and data transformation.
• Experience working with large, messy or semi-structured datasets.
• Experience building APIs/services, preferably using FastAPI, Flask or a similar framework.
• Practical experience with machine learning and NLP/text classification.
• Experience with BERT, Hugging Face Transformers or similar transformer models.
• Strong understanding of data structures, feature engineering and model evaluation.
• Ability to take a problem from raw data through to a working, testable implementation.
• Strong debugging and problem-solving skills.
• Strong understanding and experience of performance optimisation, computational efficiency and scalable data processing.
• Ability to diagnose whether a performance problem is caused by code, data processing, model inference, database queries or infrastructure.

Good to Have

• Experience with financial transactions, banking, UPI, cards or fintech.
• Experience with merchant categorisation, MCCs, entity resolution or transaction narrations.
• Experience with AWS, Docker or production ML workflows.
• Experience working with LLMs or embeddings.
• Experience working with data quality and data observability tools.
• Exposure to sustainability, emissions or household consumption data.