Description

Design, develop, and optimize Generative AI applications using AWS Bedrock and SageMaker.

This role is on-site.

Responsibilities

• Build and integrate Generative AI applications using AWS Bedrock, including prompt engineering, RAG implementation, and AI agent workflows.
• Develop backend services in Python and Node.js, enabling real-time and streaming AI responses.
• Deploy scalable AI solutions using Bedrock Knowledge Bases, integrating with S3, databases, and enterprise systems via vector search and embeddings.
• Manage the ML lifecycle with SageMaker, including feature engineering, model monitoring, drift detection, and MLOps pipeline automation.
• Implement security guardrails, content filtering, and cost optimization for token usage and model selection.

Required Skills

• 10+ years of software engineering experience.
• Expertise in AWS Bedrock, including APIs, SDKs, and agent design.
• Strong proficiency in Python (Pandas, NumPy, Scikit-learn) and Node.js.
• Hands-on experience with Amazon SageMaker Studio, Training Jobs, Endpoints, Pipelines, Model Registry, and Feature Store.
• Deep understanding of LLMs, prompt engineering, and Retrieval Augmented Generation (RAG).
• Experience with core AWS services: IAM, S3, Lambda, API Gateway, and CloudWatch.
• Knowledge of vector databases and CI/CD practices for AI applications.
• Familiarity with TensorFlow or PyTorch for model training and optimization.

Preferred Skills

• Experience with multi-step workflow automation and external API integration for AI agents.
• Strong background in Exploratory Data Analysis (EDA) and handling large datasets.

Key Skills

Education

Any Graduate