The company is looking to leverage Generative AI solutions, specifically on the AWS platform, to enhance its applications and services. This involves building scalable, serverless applications that integrate AI capabilities, requiring expertise in AI/ML, cloud services, and software development best practices.
Requirements
- Experience with AWS services (ECS, Lambda, SQS, RDS, CloudWatch etc.) is required
- AI : Experience with Gen AI solutions, AWS Bedrock, Sagemaker, GitHub Copilot/Amazon Q is required
- Extensive programming experience with Python.
- Experience with LLM orchestration Langchain is a must. DSPY and LlamaIndex is a plus.
- Experience with AWS OpenSearch, DynamoDB, SageMaker, API Gateways, ECS/Docker is a plus.
- Experience with building scalable serverless application (real-time / batch) on AWS stack (Lambda + step function).
- Basic understanding of Natural Language Processing, and Deep Learning
Responsibilities
- Experience with AWS services (ECS, Lambda, SQS, RDS, CloudWatch etc.) is required
- AI : Experience with Gen AI solutions, AWS Bedrock, Sagemaker, GitHub Copilot/Amazon Q is required
- Extensive programming experience with Python.
- Experience with LLM orchestration Langchain is a must. DSPY and LlamaIndex is a plus.
- Experience with AWS OpenSearch, DynamoDB, SageMaker, API Gateways, ECS/Docker is a plus.
- Experience with building scalable serverless application (real-time / batch) on AWS stack (Lambda + step function).
- Experience in customization techniques across various stages of the RAG pipeline, including model fine-tuning, retrieval re-ranking.
Other
- Experience Required - 8+ Years
- Experience with CI/CD pipelines, Automated Testing, Automated Deployments, Agile methodologies, Unit Testing and Integration Testing tools.
- Experience in embedding models, ANN/KNN, vector stores, database optimization, performance tuning, Retry/Circuit breaker (TPM/RPM).
