AI Engineer - Software Engineer
Core
Design and implement scalable, reliable agentic AI platforms and production-grade AI systems for enterprise workflows.
Role type
Senior IC AI Engineer (Software)
Builds
Production-grade AI systems including agents, skills, memory patterns, guardrails, and tool-use orchestration.
Domain
Financial services + Agentic AI / Cloud Infrastructure
Deliverable
production ML models | product features | infrastructure
Required skills
Large language model application development, agentic patterns, tool integrations, cloud-native service architecture, retrieval-augmented generation, embeddings, semantic search, context engineering, API development, distributed systems troubleshooting, event-driven architectures, AI system evaluation and monitoring, secure coding practices, AI-assisted development tool validation
Preferred skills
Experience with enterprise-authorized AI coding tools, knowledge of responsible AI use in engineering
Technologies
AWS, Kubernetes, Serverless, Containers, Event-driven messaging, Retrieval-augmented generation (RAG), Embeddings, Semantic search, Prompt management
Responsibilities
Design and implement components of scalable, reliable agentic AI platforms for enterprise workflows. Build production-grade AI systems including agents, skills, memory patterns, guardrails, and tool-use orchestration. Implement retrieval and context-engineering patterns such as embeddings, semantic search, grounding, summarization, and prompt/version management. Engineer cloud-native services on AWS using containers, serverless compute, and event-driven messaging patterns. Optimize latency, throughput, scalability, caching, context efficiency, and cost across large language model workloads. Develop secure, reusable APIs and integrations that connect AI capabilities to enterprise platforms and workflows. Implement evaluation, experimentation, regression testing, and observability signals to improve quality and agent behavior over time. Partner with product, platform, and engineering teams to turn requirements into resilient, measurable deliverables. Contribute to technical standards and code quality through design reviews, documentation, and peer code reviews. Use enterprise-authorized AI coding assist tools to improve code quality, delivery speed, and productivity, while validating outputs through peer review, automated testing, and secure coding standards. Apply knowledge of software development life cycle tools, including enterprise-authorized AI-assisted development and automation capabilities, to increase the value delivered through automation.
