AWS GenAI Senior Expert

Position Overview

We are seeking an experienced AWS Generative AI expert to design, develop, and implement cutting-edge AI solutions using AWS's comprehensive suite of services. The ideal candidate will combine deep technical expertise in AWS GenAI services with strong software development skills and a thorough understanding of large language models and vector databases. This role offers an opportunity to shape the future of AI implementations while working with cutting-edge technologies.

Core Responsibilities

• Design and implement end-to-end GenAI solutions using AWS Bedrock, incorporating foundation models like Claude and Titan, etc.
• Develop and optimize prompt engineering strategies for various use cases and business requirements
• Create and maintain vector search solutions using AWS OpenSearch and other vector databases
• Implement and manage knowledge bases using Amazon Kendra for enterprise search solutions
• Design and deploy serverless architectures using AWS Lambda and ECS for AI applications
• Develop and maintain Infrastructure as Code using CloudFormation
• Implement secure and scalable database solutions using RDS PostgreSQL
• Configure and manage IAM roles and permissions for secure AI service access
• Build RESTful APIs and microservices for AI application integration
• Design and implement NLP pipelines using AWS Comprehend & Guardrails
• Create automated testing frameworks for AI applications
• Develop cost optimization strategies for AI service usage
• Lead proof-of-concept development for innovative AI solutions
• Implement automated model evaluation frameworks
• Design and maintain model serving architectures
• Create model monitoring and alerting systems
• Develop custom metrics for AI system performance
• Implement model governance frameworks

Required Technical Skills

• 5+ years of experience in software development with Python
• 3+ years of hands-on experience with AWS services
• Deep expertise in:
  • AWS Bedrock and foundation models (Claude, Titan, etc.)
  • Vector databases and embedding models
  • Amazon Kendra implementation and optimization
  • OpenSearch configuration and management
  • AWS CloudFormation and Infrastructure as Code
  • Serverless architectures (Lambda, ECS)
  • IAM security and best practices
  • RDS PostgreSQL database design and optimization
  • AWS Step Functions for AI workflows
  • AWS API Gateway configuration
  • AWS Secrets Manager and Parameter Store
  • AWS Comprehend and Guardrails
  • Amazon CloudWatch for monitoring AI applications
  • Container orchestration with ECS/EKS
  • AWS Glue for ETL processes
  • Amazon Athena for data analysis
  • AWS Auto Scaling configurations
  • Amazon ECR for container registry

Essential Knowledge Areas

• Advanced understanding of prompt engineering techniques and best practices
• Comprehensive knowledge of LLM capabilities, limitations, and optimal use cases
• Experience with RAG (Retrieval-Augmented Generation) implementations
• Expertise in vector similarity search and semantic search concepts
• Strong understanding of AI/ML deployment patterns and architectures
• Knowledge of AI security best practices and responsible AI principles
• Expertise in AI model evaluation and performance metrics
• Understanding of AI model governance and compliance requirements
• Knowledge of AI/ML cost optimization techniques
• Understanding of AI data privacy and security considerations
• Experience with AI model monitoring and debugging
• Expertise in model serving architectures
• Knowledge of PII detection and redaction
• Expertise in implementing AI Guardrails
• Knowledge of model performance optimization
• Expertise in data preprocessing pipelines
• Understanding of model evaluation metrics
• Understanding of model governance frameworks

Required Experience

• Proven track record of successfully delivered GenAI projects
• Experience with enterprise-scale AI implementations
• Background in creating production-ready AI solutions
• History of optimizing AI model performance and cost
• Experience with real-time AI inference systems
• Track record of successful AI system architecture design
• Experience with AI system performance tuning
• Background in AI project estimation and planning
• History of successful stakeholder management in AI projects
• Experience with AI system troubleshooting and debugging
• Track record of successful model deployments
• Experience with model monitoring systems
• Background in model governance implementation
• History of successful model optimization
• Track record of successful data pipeline design
• Background in model experiment design
• Background in model performance optimization
• Background in model governance frameworks

Soft Skills

• Strong problem-solving and analytical abilities
• Excellent communication skills for explaining technical concepts to non-technical stakeholders
• Ability to lead technical discussions and mentor team members
• Strong documentation and technical writing skills
• Experience working in Agile environments
• Leadership skills for guiding AI initiatives
• Ability to influence and drive technical decisions
• Strong presentation skills for executive-level communications
• Excellent project management capabilities
• Capacity to work effectively in cross-functional teams
• Ability to mentor and guide junior AI developers
• Skills in facilitating technical design sessions
• Experience in conducting technical interviews
• Conflict resolution abilities
• Strategic thinking capabilities
• Change management skills
• Risk assessment abilities
• Decision-making capabilities
• Time management skills
• Team building abilities

Additional Requirements

• Bachelor's or Master's degree in Computer Science, Software Engineering, or related field
• Ability to work in a fast-paced environment with rapidly evolving technologies
• Willingness to stay current with AWS AI service updates and new features
• Availability for occasional off-hours support during critical deployments
• Ability to work across different time zones if necessary
• Commitment to continuous learning and professional development
• Willingness to contribute to technical blogs and knowledge sharing