AI Software Engineer (Python & GenAI)
Yubi
About Us
Job Description
Yubi, formerly known as CredAvenue, is re-defining global debt markets by freeing the flow of finance between borrowers, lenders, and investors. We are the world's possibility platform for the discovery, investment, fulfillment, and collection of any debt solution. At Yubi, opportunities are plenty and we equip you with tools to seize it.
In March 2022, we became India's fastest fintech and most impactful startup to join the unicorn club with a Series B fundraising round of $137 million.
In 2020, we began our journey with a vision of transforming and deepening the global institutional debt market through technology. Our two-sided debt marketplace helps institutional and HNI investors find the widest network of corporate borrowers and debt products on one side and helps corporates to discover investors and access debt capital efficiently on the other side. Switching between platforms is easy, which means investors can lend, invest and trade bonds - all in one place. All of our platforms shake up the traditional debt ecosystem and offer new ways of digital finance.
About the Role
We are looking for an experienced Python Engineer with a passion for building intelligent, agentic systems to join our engineering team. You will not just be writing scripts; you will be architecting scalable microservices and building the next generation of AI-powered features. This role is perfect for a builder who loves clean code, understands distributed systems, and has hands-on experience with Generative AI—specifically RAG pipelines, autonomous agents, and MCP (Model Context Protocol) and agent evals.
Key Responsibilities
Architect & Build: Design and develop scalable microservices using Python. You will own the lifecycle of these services from design to deployment on AWS EKS.
GenAI Implementation: Build and optimize Agentic workflows and RAG (Retrieval-Augmented Generation) pipelines. You will work on enabling LLMs to interact with external tools and data via Tool Calling.
Standards & Protocols: Implement and maintain MCP (Model Context Protocol) servers to standardize how our AI agents interface with our data and tools.
Quality Assurance: Set up and run Evals (LLM evaluations) to ensure the reliability and accuracy of our AI outputs.
Code Quality: Champion clean code principles. You will write maintainable, self-documenting code and participate in rigorous code reviews.
Infrastructure: Deploy and manage applications using the AWS stack (Lambda, ECS/EKS, API Gateway, etc.).
What We Are Looking For
Must-Have Qualifications
Experience: 3–5 years of professional software development experience.
Core Python: Deep expertise in Python. You understand asynchronous programming (asyncio), type hinting, and modern Python design patterns.
Microservices: Proven experience designing loosely coupled microservices. You understand REST APIs, event-driven architecture, and containerization (Docker).
Generative AI Stack:
Hands-on experience building RAG systems.
Experience working with Vector Databases (e.g., Pinecone, Milvus, Qdrant, or pgvector).
Understanding of Tool Calling/Function Calling with LLMs.
Experience setting up Evals to test model performance.
Specific Requirement: Familiarity with or implementation of MCP (Model Context Protocol) servers.
Cloud (AWS): Solid experience with AWS services, particularly serverless and container orchestration.
Highly Preferred
Public Portfolio: A GitHub profile demonstrating your coding style, open-source contributions, or personal AI/LLM projects. Please include this in your application.
Experience with orchestration frameworks like LangChain, LangGraph, or LlamaIndex.
Knowledge of Infrastructure as Code (Terraform or CDK).