Generative AI Engineer

About the Role

We are looking for a GenAI Developer to build scalable, production-ready AI applications, working on LLM pipelines, RAG systems, vector databases, and backend services.

Key Responsibilities

Build and optimize GenAI solutions using LangGraph, OpenAI SDK, LiteLLM

Design LLM workflows, agents, and prompt pipelines

Implement RAG using embeddings and vector search

Develop backend services using FastAPI / Django

Build APIs, microservices, and automation pipelines

Work with vector databases (ChromaDB, Qdrant, etc.)

Integrate AI APIs (OpenAI, AWS Bedrock, Azure AI)

Ensure performance, scalability, and clean code practices

Required Skills

1–4 years in AI/ML, GenAI, or backend development

Strong knowledge of LLMs, RAG, embeddings, and agent frameworks

Proficiency in Python, FastAPI / Django

Experience with vector databases

Experience with API integrations

Good understanding of SQL & NoSQL

Good to Have

Cloud: AWS, Azure, GCP

Docker, Kubernetes, CI/CD

Monitoring tools (Grafana, Prometheus)

Experience in conversational AI