Backend AI Engineer: Scalable Inference & APIs

USA Tech Recruit; San Francisco (CA); Vor Ort; USD 150.000 - 210.000; Vollzeit

Zusammenfassung

USA Tech Recruit is seeking a Backend Engineer, AI to join a fast-growing AI-first technology company building the production infrastructure behind next-generation AI applications powered by large language models.

You will design inference pipelines, orchestration layers, and high-performance APIs that connect cutting-edge models with real-world products, while optimizing latency, reliability, and observability in scalable systems.

Qualifikationen

• Experience with AI inference pipelines and model orchestration.
• Experience building high-throughput, low-latency backend systems.
• Proficient with SQL and NoSQL databases.
• Experience with monitoring, logging and observability.
• Strong API design and backend architecture skills.
• Knowledge of performance optimisation, caching and streaming.

Aufgaben

• Build and operate backend systems powering AI interactions at scale.
• Design inference pipelines and orchestration layers.
• Develop high-performance APIs connecting models with products.
• Optimize latency, reliability, and throughput of AI services.
• Collaborate with ML and product teams to deliver scalable observability.

Kenntnisse

AI inference pipelines

Model orchestration

High-throughput backend

SQL

NoSQL

Observability

API design

Performance optimisation

Jobbeschreibung

USA Tech Recruit is seeking a Backend Engineer, AI to join a fast-growing AI-first technology company building the production infrastructure behind next-generation AI applications powered by large language models.

You will design inference pipelines, orchestration layers, and high-performance APIs that connect cutting-edge models with real-world products, while optimizing latency, reliability, and observability in scalable systems.