Senior Backend Engineer - Production AI on Azure

BrickRed Systems LLC; New York (NY); Sur place; USD 150 000 - 210 000; Plein temps

Résumé du poste

BrickRed Systems is seeking a Senior Software Engineer to lead backend services at scale, focusing on Python, Azure, and AI-driven systems in production. You will own end-to-end delivery, reliability, and performance of critical systems.

You will design and operate distributed architectures, integrate RAG pipelines and LangChain workflows, and collaborate across teams to ensure robust incident response and continuous deployment in a fast-paced environment.

Qualifications

• 8–10+ years of backend or distributed systems engineering experience with ownership of production systems.
• Strong Python proficiency including performance optimization and production reliability.
• Extensive Azure production experience beyond certifications or labs.
• Experience in incident management and on-call rotations.

Responsabilités

• Design, develop, and maintain production‑grade Python services for reliability and observability.
• Build and operate Azure-native distributed systems using Functions, Durable Functions, Event Grid, and Service Bus.
• Develop production-ready AI applications including RAG pipelines and LLM orchestration.
• Investigate and resolve production incidents using tracing, logs, and monitoring tools.
• Establish standards for code reviews, automated testing, CI/CD, and safe deployments.
• Identify performance bottlenecks and scaling challenges in distributed systems.
• Collaborate across tech stacks, including C#, as needed.

Connaissances

Python

Azure

Distributed systems

Production-grade AI

Outils

Azure Functions

Durable Functions

Event Grid

Service Bus

LangChain

Description du poste

BrickRed Systems is seeking a Senior Software Engineer to lead backend services at scale, focusing on Python, Azure, and AI-driven systems in production. You will own end-to-end delivery, reliability, and performance of critical systems.

You will design and operate distributed architectures, integrate RAG pipelines and LangChain workflows, and collaborate across teams to ensure robust incident response and continuous deployment in a fast-paced environment.