Full-Stack - GenAI

Location:- Bangalore - Whitefield

Experience:- 5–8 years

About the Role

End-to-end developer responsible for building GenAI/AI-powered proof-of- concepts, prototypes, and applications within the innovation POD.

Will work closely with the Innovation Manager and Data Science/Prompt Engineer to deliver functional solutions rapidly. The role requires someone who can independently take an idea from concept to working prototype.

Key Responsibilities

- Design and develop end-to-end PoC solutions covering both frontend and backend
- Build AI-powered applications, dashboards, and automation tools
- Integrate GenAI/LLM APIs and services into business applications
- Deploy and manage solutions on Microsoft Azure cloud platform
- Collaborate with the Data Science/Prompt Engineer to build AI-driven features
- Ensure code quality, documentation, and reusability of solutions
- Participate in innovation brainstorming and technical feasibility assessments
- Present technical demos and walkthroughs to client stakeholders

Must-Have Skills

- 5–8 years of full-stack development experience
- Strong proficiency in Python
- Strong proficiency in React (frontend)
- Experience with Microsoft Azure stack (Azure App Services, Azure Functions, Azure AI Services)
- Experience integrating REST APIs and working with microservices architecture
- Knowledge of databases (SQL and NoSQL)
- Good communication skills for client-facing interactions

Good to Have

- Experience with Azure OpenAI Service and Azure AI Foundry
- Familiarity with CI/CD pipelines and Azure DevOps
- Curiosity to test latest technologies for both implementing and enhancing work (Codex, GPT, Copilot)

● Develop and deploy scalable Generative AI and LLM-based solutions on Azure or GCP or AWS





● Agentic AI Development: Design, build, and deploy agentic AI systems using frameworks such as LangChain, LangGraph, and related libraries. Develop and deploy multi-agent systems capable of autonomous decision-making,

reasoning, planning, and collaboration.

● RAG Pipelines: Implement and optimize retrieval-augmented generation (RAG)

systems, ensuring agents can access and incorporate external knowledge sources for grounded, accurate responses.

● Integrate AI models with business applications and build scalable APIs (e.g.,

FastAPI, Flask) and microservices.

● Lead the development of enterprise-grade AI platforms integrating LLMs, RAG,

embeddings, and agentic AI protocols.

● Implement and standardize Model Context Protocol (MCP) for consistent context management across models and agents.

Required Skills & Qualifications

● Programming: Strong proficiency in Python is mandatory, including OOP concepts and best coding practices.

● Cloud Expertise: Delivered Gen AI or ML projects in cloud(AWS/GCP/Azure)

● AI Frameworks: Familiarity with LLM frameworks and libraries such as Google

ADK, LangChain, LlamaIndex, or similar frameworks.

● AI Techniques: Solid understanding of RAG architectures, prompt engineering,

model optimization, and performance evaluation methodologies.

● Infrastructure: Experience with MLOps practices, CI/CD pipelines,

containerization (Docker/Kubernetes), and infrastructure automation tools like

Terraform is a plus.

If you're interested in this opportunity, please share your updated CV at [Confidential Information] or WhatsApp it to (phone hidden).

Stay updated with our latest job opportunities and company news by following us on LinkedIn:

https://www.linkedin.com/company/sourcebae

📌 Full Stack Engineer (Bengaluru)
🏢 Sourcebae
📍 Bengaluru