Full-Stack AI Engineer: Real-Time AI Engines & Integration

Evolent; United States; On-site; USD 115,000 - 135,000; Full time

Benefits offered by this job

Health insurance benefits

Comprehensive benefits

Job summary

Evolent is hiring a software engineer to design and build the adaptor layer between AI service engines and the enterprise service bus, enabling real-time AI workloads and production-grade LLM agents. The role focuses on building, deploying, and maintaining AI services with strong CI/CD, testing, monitoring, and security practices.

The candidate will integrate LLM APIs (Azure/OpenAI) into production workflows, work in an Agile environment, and handle PHI or sensitive data per compliance

Qualifications

• Bachelor's degree in CS, Software Engineering, or related field or equivalent experience.
• 3–5+ years of software engineering experience.
• Strong Python and experience with at least one other modern language (TypeScript, C#, Java, or Go).

Responsibilities

• Design and build the adaptor layer between AI service engines and the enterprise service bus, including construction and handling of FHIR PAS payloads.
• Build a new synchronous service engine for real-time AI workloads, adapting the architecture of the Triage engine.
• Build, deploy, and operate LLM-based agents on the service engines; manage production readiness from configuration to deployment.
• Support and maintain the existing production Triage services: bug fixes, upgrades, releases, and health.
• Integrate LLM and generative AI services into production business workflows.
• Implement CI/CD, automated testing, monitoring, and observability for AI services; contribute to dashboards and alerting.

Skills

Python

RESTful APIs

Agile development

CI/CD

LLM APIs integration

TypeScript

Education

Bachelor's degree in Computer Science, Software Engineering, or related field

Tools

Azure

Docker

Kubernetes

OpenTelemetry

Job description

Evolent is hiring a software engineer to design and build the adaptor layer between AI service engines and the enterprise service bus, enabling real-time AI workloads and production-grade LLM agents. The role focuses on building, deploying, and maintaining AI services with strong CI/CD, testing, monitoring, and security practices.

The candidate will integrate LLM APIs (Azure/OpenAI) into production workflows, work in an Agile environment, and handle PHI or sensitive data per compliance