Description :

Job Summary :

We are looking for a GenAI Engineer with strong hands-on experience in building and deploying Generative AI solutions using Python and AWS. The ideal candidate will have solid exposure to Retrieval-Augmented Generation (RAG) architectures and experience working with AWS Lambda and Amazon Bedrock to develop scalable, production-ready GenAI applications.

Key Responsibilities :

- Design, develop, and deploy Generative AI applications using Python

- Build and optimize RAG-based solutions using vector databases and embedding models

- Integrate and manage LLMs using Amazon Bedrock

- Develop serverless GenAI workflows using AWS Lambda

- Implement prompt engineering, model orchestration, and response optimization

- Ensure scalability, performance, security, and cost efficiency of GenAI systems

- Collaborate with product managers, data scientists, and backend teams

- Monitor, evaluate, and improve model outputs and system reliability

- Document architecture, workflows, and best practices

Mandatory Skills :

- Strong proficiency in Python

- Hands-on experience with AWS (especially Lambda)

- Solid experience with Retrieval-Augmented Generation (RAG)

- Practical experience using Amazon Bedrock

- Understanding of LLM concepts, embeddings, vector search, and prompt engineering

Good to Have :

- Experience with vector databases (FAISS, Pinecone, OpenSearch, etc.)

- Knowledge of LangChain / LlamaIndex

- Experience with API integration and microservices

- Exposure to CI/CD and cloud-native architectures

- Understanding of data security, governance, and compliance in AI systems

Education :

- Bachelors or Masters degree in Computer Science, Engineering, or a related field