Senior AWS Bedrock & SageMaker Developer

Descriptions:
" Develop, integrate, and optimize Generative AI applications using AWS Bedrock, including prompt engineering, RAG implementation, and AI agent workflows.
Create and optimize prompts for LLMs
Work with Amazon Bedrock APIs for model inference
Develop backend services using Python / Node.js
Enable real-time and streaming AI responses
Build AI solutions using Bedrock Knowledge Bases
Integrate with data sources (S3, databases, enterprise systems)
Implement vector search and embeddings
Design and build AI agents using Bedrock Agents
Implement multi-step workflows and task automation
Integrate external APIs/tools into AI workflows
Work with core AWS services:
o IAM (security & access control)
o S3 (data storage)
o Lambda (serverless compute)
o API Gateway (service exposure)
Deploy scalable and secure AI solutions
Implement guardrails and content filtering
Ensure data privacy, compliance, and safe AI usage
Optimize token usage and model selection
Monitor and control Bedrock usage costs
Convert business requirements into AI-driven solutions
Manage and utilize SageMaker Feature Store for reusable feature engineering
Monitor model performance and detect data drift in production systems
Maintain and retrain models for continuous performance improvement
Track experiments, metrics, and ensure model reproducibility
Integrate SageMaker with AWS services like S3, IAM, Lambda, and CloudWatch
Optimize infrastructure, performance, and cost of ML workloads
Collaborate with cross-functional teams to design and deliver ML solutions"

"Generative AI & LLM Fundamentals, Prompt Engineering, Bedrock API and SKD usage, RAG, AI Agents and workflow design,
Programming skill (Python, APIs, Microservice), AWS core knowledge (IAM, S3, Lambda, API Gateway), Application integration skills, Vector databases, CI/CD for AI Apps.
Understanding of ML life cycle, Strong coding in Python, Good knowledge on Py libraries (Pandas, Numpy, Scikit-learn (ML), Tensorflow/PyTorch),
Exploratory Data Analysis (EDA), Handling large dataset in Amazon S3, Model Training and Optimization, Model deployment, MLOps & Pipeline Automation.
Hands on SageMaker Studio, Training Jobs, Endpoints, Pipeline, Model registry, Feature Store
Hands on AWS Core services (S3, IAM, EC2, Lambda, Cluodwatch)"


Skills: Digital : Python~Digital : Amazon Web Service(AWS) Cloud Computing~Digital : DevOps~Github Enterprise
Experience Required: 10 & Above