About Aplazo

Aplazo, a Mexican BNPL startup, offers a unique solution for an underbanked Population. Unlike its international counterparts, Aplazo isn't just about debt - it's an alternative to cash for many Mexicans. Founded four years ago, Aplazo allows users to make fractionated payments online and in stores, even without a credit card. We are on a mission to unlock financial access, freedom, and opportunity for every Mexican. Now our users can have what they want and when they want. Aplazo allows its consumers to live their ideal lifestyle, making it easier to acquire the products they want. Through our platform, consumers can split their online and offline purchases into multiple installments without needing a credit card and avoiding the debt trap.

In-store transactions account for more than half of Aplazo's business, highlighting the limited reach of e-commerce in Mexico. Aplazo's success is attributed to its focus on data and technology. By leveraging AI, the company has been able to limit credit loss despite its rapid growth. Notably, 40% of Aplazo's users have no credit history, making traditional credit checks irrelevant. This is a major hurdle for international BNPL players who may struggle in the Mexican market.

Aplazo has recently received Series B funding of $70 Million USD and Series A+ funding of $27.5 Million USD in 2022 With a total of $110 million raised Aplazo is well-positioned for continued growth and innovation in the Mexican fintech landscape and its team is growing in each vertical. We are setting out to make an impact on an epic scale. Aplazo enables merchants to connect with consumers in a creative, purposeful way, building more loyalty and trust between them. Aplazo's integrated, tech-enabled platform offers merchants the ability to increase average basket size, conversion, and customer engagement.

Aplazo Story in Techcrunch : https://techcrunch.com/2024/05/13/aplazo/

About ML & AI Labs

At Aplazo, our ML & AI team is a cornerstone of our technological innovation and strategic decision-making. We pride ourselves on our technical maturity and high proficiency in addressing complex and critical business challenges. Our team is dedicated to solving high-stakes problems across various domains, including risk and payments, merchants, B2C, personalisation, growth and marketing, recommendation systems, customer support, collections, underwriting, credit life cycle management, and fraud detection.

Aplazo ML & AI lab has been instrumental in the development of state-of-the-art credit risk and fraud detection models. The risk and payment machine learning models suite has leveraged advanced data science and AI algorithms to achieve best-in-class prediction capabilities. Aplazo has adopted best practices in MLOps, creating a seamless workflow for model development, deployment, and monitoring. This includes automated CI/CD pipelines, version control for models and data, and robust monitoring and logging systems. We have built a sophisticated ML engineering infrastructure that supports scalable model training, testing, and deployment. This infrastructure ensures the high availability, reliability, and performance of our machine learning solutions.

Our expertise in developing advanced recommendation models has significantly enhanced user engagement, driving more personalised and meaningful interactions with our platform. We have also created sophisticated propensity and activation probability models, enabling us to optimise Customer Acquisition Cost (CAC) effectively. These models help us target the right customers with the right offers at the right time, maximising our marketing efficiency.

Moreover, we have engineered cutting-edge data science tools to deepen our understanding of the relationships within our consumer base. These insights have been instrumental in refining our referral programs, leading to increased customer retention and satisfaction. Our commitment to leveraging data science for continuous improvement and innovation ensures that Aplazo remains at the forefront of delivering exceptional value to our customers and stakeholders.

Notable Achievements :

1. We achieved the lowest fraud rate in LATEM markets by leveraging the very high capabilities of our multiple fraud detection models with real-time inferencing
2. Alternative data lending - built capabilities to extend credits to the underbanked segment in Mexico markets fostering financial inclusion and financial freedom for everyone
3. Advanced reinforcement learning models and deep learning models to achieve hyper-personalisation for credit limit changes
4. Incorporated Dynamic Risk Based Pricing model to optimise customer conversion rate
5. Developed recommendation engine to personalise all communication to end user

Role Mission :

• Develop highly scalable credit and fraud risk models and tools leveraging machine learning, deep learning, and rules-based models.
• Work closely with product and operation teams to implement new risk reduction practices using ML & DL.
• Build state of the art risk models using alternative data such as android device data, bank statements data, etc.
• Own the Data Science model end-to-end, from data collection to model building, to monitoring the model in production.
• Build Machine Learning and Deep Learning models in the customer lifecycle which include Personalization, Recommendation, Rewards, Referrals, Transaction Categorization, Customer Science-related models.
• Understands the End to End ML pipeline ( data gathering to production ) basic understanding of production level coding practices
• Data acquisition and Stakeholder Management: Evaluate and identify superior data sources, perform ROI estimations for data vendor partnerships, and collaborate with commercial and business teams to align data strategies and meet their needs.
• Conduct Data Analyses; your analyses will decide which policies we adopt, where we expand our business, and with whom we partner.

Required Qualifications:

Experience:

• Proven experience in risk management within consumer lending, buy-now-pay-later, payment, or credit card sectors.
• Experience in statistical modeling, machine learning, data mining, unstructured data analytics, and natural language processing. Sound understanding of - Bayesian Modeling, Classification Models, Cluster Analysis, Neural networks, Nonparametric Methods, Multivariate Statistics,NLP etc.
• Experience with common libraries and frameworks in data science
• Experience with pre-trained language models (e.g., BERT, GPT-3, GPT-4, T5).
• Production level deployment (ML engineering, OOPs)
• Collaborate with Platforms and Engineering to make sure the ML models built are deployed and integrated into the systems.
• Ability to work in a high ownership environment, the right candidate should have competency to work independently as well as collaboratively with the team.

Years of experience:

• 6 to 12 years of relevant work experience.

Technical skills:

• Proficient in Python programming, with a focus on coding for machine learning and deep learning applications.
• Strong in data analysis and data wrangling.
• Familiarity with database queries and data analysis processes (SQL, Python)
• Follow industry best practices, and stay up to date with the latest machine learning/ GenAI algorithms and techniques to drive innovation.
• Knowledge of deep learning concepts like CNN, RNN, tokenization, transformers, and various NLP techniques

Soft skills:

• Outstanding leadership, influencing, communication, interpersonal, and teamwork skills.
• Detail-oriented, with the ability to work both independently and collaboratively.
• Excellent communication skills, including the ability to explain complex concepts to technical and non-technical stakeholders.

Academic background (studies or certifications):

• Bachelors or Master’s degree in Computer Science, Information management, Statistics or related field
• Or Doctorate in Data Science, Mathematics, Statistics, Econometrics, Economics, Operations Research, Computer Science, or related field AND 6+ years data-science experience

Nice to have

• Publications or presentations in recognised Machine Learning and Data Science journals/conferences.
• Experience with cloud services (like AWS or Google Cloud) and understanding of distributed systems.
• Exposure to GenAI models.
• Spanish

Languages:

• English (Level: advanced)