Production-Grade AI Applications Engineer

JPMorganChase; Taguig; Hybrid; PHP 1.000.000 - 1.800.000; Vollzeit

Benefits dieser Stelle

Health insurance

Zusammenfassung

JPMorganChase is seeking an AI Applications Developer to design and deliver production-grade AI solutions that leverage model-driven capabilities for real business needs. You will partner with cross-functional teams to move from discovery to launch with security, scalability, and governance in mind.

Responsibilities include building agent-based systems, refining prompts and guardrails, grounding model outputs with trusted data sources, and ensuring observability and reliability in production

Qualifikationen

• Proven experience building production-grade AI applications.
• Hands-on Python development with testable code.
• Experience deploying intelligent apps using large language models.

Aufgaben

• Design and deliver production-grade AI applications powered by LLMs.
• Build agent-based systems for complex workflows across tools.
• Develop prompts, evaluation methods, and guardrails for reliability.
• Implement retrieval-augmented generation grounded in data sources.
• Integrate with cloud services, data stores, and APIs end-to-end.
• Collaborate with product, data, engineering and governance teams.
• Apply secure-by-design practices including access controls.
• Create tests, monitoring, and observability for production quality.
• Document architectures and runbooks to enable reuse.
• Troubleshoot performance and model quality; iterate improvements.

Kenntnisse

Python development

LLM knowledge

Prompt design

Agent frameworks

Retrieval-augmented generation

Docker / containerization

Cloud services

Secure development

System observability

Tools

Kubernetes

AWS / cloud stack

SQL / databases

Jobbeschreibung

JPMorganChase is seeking an AI Applications Developer to design and deliver production-grade AI solutions that leverage model-driven capabilities for real business needs. You will partner with cross-functional teams to move from discovery to launch with security, scalability, and governance in mind.

Responsibilities include building agent-based systems, refining prompts and guardrails, grounding model outputs with trusted data sources, and ensuring observability and reliability in production