Lead Engineer ( Agentic AI)
ABOUT YUBI
Yubi (formerly CredAvenue) is redefining global debt markets by freeing the flow of finance between borrowers, lenders, and investors — the world's possibility platform for the discovery, investment, fulfilment, and collection of any debt solution. In March 2022, we became India's fastest fintech unicorn with a $137M Series B. Our platforms — Yubi Credit Marketplace, Yubi Invest, Financial Services Platform, Spocto, and Corpository — serve 17,000+ enterprises and 6,200+ investors, facilitating over ₹1,40,000 crore in debt volumes. Backed by Insight Partners, Sequoia Capital, Dragoneer, B Capital, LightSpeed, and Lightrock.
ROLE OVERVIEW
As a Lead Engineer (Agentic AI) at Yubi, you will architect and deliver production-grade intelligent systems that redefine how debt capital flows between borrowers, lenders, and investors. You will lead a pod of engineers, own the technical roadmap for key AI agent capabilities, and work hand-in-hand with Product and Data Science to bring ambitious ideas to life at scale. This role demands deep full-stack expertise across Java, a strong grasp of LLM orchestration, and the leadership instinct to elevate the entire team around you.
KEY RESPONSIBILITIES
Technical Leadership & Architecture
Own the end-to-end architecture of multi-agent systems — from LLM reasoning layers to React dashboards, Python, and Java microservices.
Define technical standards, design patterns, and coding practices for the AI platform engineering pod.
Lead design reviews, ensuring systems are scalable, secure, observable, and maintainable.
Evaluate emerging AI frameworks and tools; make adoption decisions that balance innovation with production reliability.
Drive migration of rule-based financial workflows to LLM-native agentic pipelines.
Agentic AI Engineering
Architect multi-agent orchestration using LangGraph, AutoGen, or CrewAI — supporting tool use, memory, planning, and reflection loops.
Design stateful agent memory systems combining short-term context windows with long-term vector stores for financial workflows.
Build reliable prompt engineering strategies with versioning, A/B testing, and rollback capabilities.
Implement compliance-aware guardrails: PII masking, hallucination detection, regulatory disclosure injection.
Oversee RAG pipeline design — chunking strategies, embedding model selection, retrieval optimisation, and re-ranking.
People & Delivery
Lead, mentor, and grow a team of 3–6 engineers; conduct regular 1:1s, code reviews, and career development conversations.
Drive sprint planning, estimation, and delivery commitments in close partnership with the Product Manager.
Participate in senior technical hiring — define interview criteria and assess engineering bar.
Requirements
REQUIRED SKILLS & QUALIFICATIONS
Technical
5–8 years of full-stack engineering experience, with at least 1-2 years in AI/LLM product development.
Very strong problem solving capability . Doing HLD and LLD for a given problem
Good understanding of data structures , algorithms
Good Understanding of CI/CD pipelines and test driven development
Proven experience building production LLM-powered products — prompt engineering, agent orchestration, output validation.
Hands-on with LangChain, LangGraph, AutoGen, or equivalent agent frameworks.
Strong understanding of RAG, vector search, and embedding-based retrieval.
Experience with Kafka or similar message brokers; familiarity with event-driven architecture patterns.
Kubernetes, Docker, and cloud-native AWS experience at production scale.
Leadership & Soft Skills
Proven track record of leading engineering teams and delivering complex projects end-to-end.
Excellent communication — able to translate AI system behaviour to product, business, and compliance stakeholders.
Strong systems thinker with the ability to decompose complex financial workflows into reliable automated steps.
B.E. / B.Tech / M.Tech in Computer Science or equivalent; advanced degree a plus.