Apply for Senior GenAI Engineer (AWS).

Position Summary

The Senior GenAI Engineer is responsible for designing, developing, deploying, and supporting enterprise-grade Generative AI solutions on AWS. This is a hands-on engineering role focused on building production-ready AI applications, agentic workflows, intelligent automation solutions, and scalable cloud-native platforms.

The successful candidate will work across software engineering, AI engineering, cloud infrastructure, and DevOps disciplines to deliver secure, robust, and maintainable solutions. They will actively contribute code, infrastructure, and deployment pipelines while providing technical leadership and mentoring to delivery teams.

This role is expected to spend the majority of its time building and deploying solutions rather than producing architecture artefacts.

Core Responsibilities

GenAI Solution Development

• Design and develop enterprise Generative AI applications.
• Build and deploy autonomous AI agents and multi-agent workflows.
• Develop Retrieval Augmented Generation (RAG) solutions using enterprise data sources.
• Integrate Large Language Models (LLMs) into business processes and applications.
• Build AI-powered assistants, copilots, and intelligent automation services.
• Implement AI guardrails, observability, evaluation, and monitoring capabilities.

Agent Framework Development

• Develop solutions using modern agentic frameworks including:
  • Strands Agents
  • LangGraph
  • Agent orchestration platforms
  • MCP integrations
• Build reusable agent components and workflow accelerators.
• Implement tool calling, planning, memory, and multi-agent collaboration patterns.

AWS Cloud Engineering

• Design and implement AI solutions using AWS-native services.
• Develop serverless architectures using:
  • AWS Lambda
  • API Gateway
  • Step Functions
  • SQS/SNS
  • EventBridge
• Deploy and manage workloads across AWS environments.
• Implement secure, scalable, and highly available cloud solutions.

Infrastructure & DevOps

• Build and maintain Infrastructure as Code using Terraform.
• Develop CI/CD pipelines for application and infrastructure deployments.
• Implement automated testing and deployment practices.
• Configure cloud monitoring, logging, alerting, and operational dashboards.
• Support platform reliability, performance tuning, and operational readiness.

Software Engineering

• Develop production-grade software solutions using Python.
• Build APIs, integrations, and backend services.
• Perform peer code reviews and quality assurance activities.
• Troubleshoot and resolve complex production issues.
• Contribute to engineering standards and best practices.

Required Experience

AWS

Strong experience with:

• AWS Lambda
• API Gateway
• Step Functions
• S3
• DynamoDB
• EventBridge
• ECR/ECS
• IAM
• CloudWatch
• Bedrock
• Secrets Manager
• VPC networking concepts

Infrastructure as Code

Experience with:

• Terraform
• GitOps practices
• Automated environment provisioning
• Multi-environment deployment strategies

Generative AI

Practical experience building:

• RAG applications
• AI agents
• Agent orchestration workflows
• Enterprise AI assistants
• Knowledge retrieval platforms
• LLM-based automation solutions

Development

Strong hands-on experience with:

• Python
• REST APIs
• JSON/OpenAPI
• Microservices architectures
• Asynchronous processing patterns
• Event-driven architectures

DevOps

Experience with:

• CI/CD pipelines
• GitHub Actions
• Containerisation
• Docker
• Monitoring and observability
• Secure software development practices

Nice to Have

• Amazon Bedrock
• Strands Agent Framework
• LangGraph
• Vector Databases
• OpenTelemetry
• Kafka
• Kubernetes
• MCP Server development
• AI evaluation frameworks
• Enterprise AI governance

What Success Looks Like

The successful candidate:

• Builds production AI solutions on AWS.
• Writes and reviews code daily.
• Designs and deploys infrastructure using Terraform.
• Leads technical delivery through hands-on contribution.
• Develops reusable GenAI capabilities and accelerators.
• Improves engineering standards across the team.
• Mentors developers while remaining actively involved in implementation.