AI Software Engineer (Python + LangGraph + RAG) – Remote, Immediate Joiner

About the Role

We’re looking for a highly skilled AI Software Engineer (2+ years of experience) to join our early-stage fintech AI startup. In this role, you’ll work on cutting-edge conversational AI systems, LLM-powered automation, and intelligent agent workflows using Python, LangGraph, and Retrieval-Augmented Generation (RAG) frameworks.

This is a hands-on engineering position where you’ll architect, build, and optimise AI-driven pipelines and chatbot systems that directly shape the user experience. If you enjoy building complex AI systems, designing reliable RAG pipelines, and experimenting with production-ready agent frameworks — this role is for you.

What You’ll Do

Design, develop, and maintain AI-driven backend services using Python.

Build, optimise, and maintain LangGraph-based agent workflows and stateful LLM applications.

Architect scalable Retrieval-Augmented Generation (RAG) pipelines including embedding generation, vector stores, document ingestion, and query orchestration.

Build and deploy chatbots and conversational AI features for fintech use cases.

Integrate APIs, LLM providers, vector databases, and orchestration tools.

Collaborate with frontend teams to deliver seamless and intelligent user interactions.

Implement robust security, monitoring, and optimisation practices for AI systems.

Leverage AI coding tools (Claude Code, Cursor, Copilot, etc.) to increase development velocity.

Participate in code reviews, testing, experiment tracking, and CI / CD workflows.

Work closely with founding team to design scalable solutions for AI-driven and finance-oriented features.

What We’re Looking For

2+ years of experience as a Software Engineer or AI Engineer.

Hands-on experience with LangGraph, LangChain, or similar agent orchestration systems.

Proven experience building and deploying RAG pipelines and LLM-powered applications.

Prior experience building chatbots or conversational agents (preferably production-grade).

Solid understanding of vector databases (Pinecone, PgVector, Chroma, etc.).

Strong expertise in Python, including FastAPI or similar backend frameworks.

Knowledge of databases (PostgreSQL, MySQL, MongoDB) and API design.

Familiarity with LLM APIs (OpenAI, Anthropic, Gemini, etc.).

Proficient in Docker, Git, and modern deployment practices.

Comfortable using AI-assisted coding tools.

Excellent communication skills and ability to work in fast-paced remote environments.

Bonus Points If You Have

Experience with asynchronous programming and Python performance optimization.

Knowledge of cloud platforms (AWS, GCP, Azure) and serverless / microservices architecture.

Prior experience in GenAI, fintech, or high-growth product environments.

Understanding of prompt engineering, evals, and model fine-tuning workflows.

What You’ll Get

Opportunity to work in an early-stage fintech AI startup — influencing core product direction.

High ownership and visibility across engineering and product functions.

Mentorship and collaboration with senior AI engineers.

Flexible and fully remote working environment.

Fast career growth and potential to become a long-term core team member.

We highly prefer candidates who actively leverage AI coding assistants in their workflow and take significant ownership in their day-to-day work.