TL;DR
Fullstack Software Engineer (AI): Develop and enhance banking applications with generative AI capabilities, integrating LLMs and building advanced AI features in Python backend and React frontend. Focus on designing scalable AI-driven services, implementing RAG patterns, and secure development practices in a fintech environment.
Location: Onsite in Bengaluru, India
Company
hirify.global is an outsourcing company working with a major British bank to develop and upgrade digital banking applications.
What you will do
- Design, develop, and maintain Python backend services using FastAPI.
- Integrate large language models (LLMs) for AI-driven features.
- Build scalable React frontends with performance optimizations.
- Implement retrieval-augmented generation (RAG) and streaming AI responses.
- Develop and consume REST and GraphQL APIs including real-time features.
- Manage containerized deployments with Docker, Kubernetes, and Helm.
- Apply secure development best practices including OWASP guidelines and authentication mechanisms.
Requirements
- 4–9 years of professional development experience.
- Expert-level Python and FastAPI experience.
- Strong React.js and modern JavaScript/TypeScript skills.
- Experience with REST/GraphQL APIs and real-time features.
- Knowledge of containerization and orchestration tools.
- Secure development practices including OWASP, JWT/OIDC, and input validation.
Nice to have
- Experience integrating LLMs (Amazon Bedrock, Snowflake Cortex, LangChain).
- Building RAG-based features and AI-powered chat interfaces.
- AWS services and event-driven architecture experience.
- Financial services or regulated environment experience.
Culture & Benefits
- Vacation and sick pay as per local laws.
- Health insurance support.
- Time off for state holidays.
- Corporate parties and social events.
- Support for IT certifications and learning platforms.
Будьте осторожны: если вас просят войти в iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →