AI-Directed Software Engineer

As an AI-Directed Software Engineer, you will build and deliver production-ready software by leveraging artificial intelligence to accelerate development across the full technology stack. You will take ownership of features from initial concept through implementation, testing, deployment, and production operations, working across backend services, frontend applications, databases, and cloud infrastructure.

Using AI coding tools as your primary implementation engine, you will transform product requirements into clearly defined tasks and guide AI-generated solutions toward reliable, secure, and scalable outcomes. You will also develop intelligent agent workflows using Amazon Bedrock, integrating advanced AI capabilities directly into software products.

This role combines full-stack engineering, cloud architecture, DevOps, and applied AI in a fast-moving, innovation-driven environment. You will help establish repeatable AI-directed development practices, improve delivery speed, and shape the future of software engineering.

Accountabilities

• Own the end-to-end delivery of software features, from requirements and technical specifications to demonstrations, production releases, and ongoing maintenance.
• Direct AI coding tools to generate and refine code across backend services, frontend applications, database queries, APIs, infrastructure configurations, and development workflows.
• Break down complex product requirements into structured, specification-driven tasks that AI systems can execute efficiently and consistently.
• Review, test, debug, and harden AI-generated code to ensure correctness, reliability, security, performance, and production readiness.
• Develop and maintain backend services using technologies such as Java, REST APIs, and related frameworks, while contributing to frontend applications built with Angular, React, and TypeScript.
• Design and optimize database schemas, SQL queries, and data flows, primarily using PostgreSQL.
• Configure, deploy, and operate applications and services on AWS, using infrastructure-as-code practices and cloud services such as CloudFormation, IAM, VPC, S3, EFS, and CloudWatch.
• Build and maintain containerized applications using Docker and Kubernetes, including deployment configurations managed through Helm or Kustomize.
• Design and implement AI-powered agents using Amazon Bedrock, including model integrations, action groups, tool calling, and Knowledge Bases for retrieval-augmented generation (RAG).
• Implement appropriate safeguards for AI agents, including guardrails, evaluation frameworks, failure handling, and human-in-the-loop checkpoints for consequential decisions.
• Monitor application reliability, cloud resource utilization, AI token consumption, and infrastructure costs to ensure efficient and sustainable operations.
• Apply security best practices, including least-privilege access controls, secure integrations, and careful validation of AI-generated infrastructure and application code.
• Improve observability and troubleshooting through logging, monitoring, testing, and operational tooling.
• Establish and document reusable AI-directed development workflows, prompts, evaluation methods, and engineering standards.
• Continuously improve development throughput, cycle time, and delivery consistency across assigned workstreams.
• Collaborate with colleagues to challenge assumptions, resolve technical problems, and promote effective adoption of AI-directed software development practices.

Requirements

• Strong software engineering fundamentals, including API design, distributed systems, debugging, data flows, and system architecture.
• At least three years of hands-on AWS experience building, deploying, and operating production workloads.
• Practical knowledge of AWS security and infrastructure, including IAM permissions, VPC networking, service reliability, cloud resource management, and cost optimization.
• Experience with infrastructure as code on AWS, preferably using CloudFormation. Familiarity with AWS CDK or Terraform is also acceptable.
• Broad full-stack engineering capabilities, with the ability to move between backend services, frontend development, database work, and deployment configuration.
• Working knowledge of containers and Kubernetes, including the ability to troubleshoot failing pods, interpret deployment manifests, and modify Helm configurations. Candidates should be comfortable developing these skills quickly if needed.