Backend Engineer, Scalable AI Inference & APIs

Salt Digital Recruitment; United States; On-site; USD 140,000 - 190,000; Full time

Job summary

Salt Digital Recruitment is seeking a Backend Engineer - AI Systems to own inference and orchestration layers powering AI interactions across the platform. You will design and operate production systems linking AI models with backend infrastructure for fast, reliable services used by mobile and desktop apps.

You will work on latency, scalability, and observability while collaborating with AI/ML teams to bring new capabilities into production.

Qualifications

• Strong backend engineering fundamentals and production systems experience.
• Experience delivering high-throughput, low-latency services at scale.
• Familiarity with AI inference patterns including LLMs and multimodal models.

Responsibilities

• Build and operate backend systems supporting AI-powered features in production.
• Design scalable inference pipelines, orchestration layers and service boundaries around AI models.
• Develop reliable APIs that integrate with frontend and ML systems.
• Optimize latency and throughput across inference, caching, batching and streaming.
• Own production concerns including monitoring, logging, alerting and incident response.
• Troubleshoot complex issues across distributed systems under load.
• Improve system performance using production data and usage metrics.
• Collaborate with engineering and AI/ML teams to bring new AI capabilities to production.

Skills

Backend systems

Low-latency services

Distributed systems

API design

Performance optimization

Observability

ML/AI collaboration

Tools

Kubernetes

Docker

PyTorch

SQL

NoSQL

LLM frameworks

Job description

Salt Digital Recruitment is seeking a Backend Engineer - AI Systems to own inference and orchestration layers powering AI interactions across the platform. You will design and operate production systems linking AI models with backend infrastructure for fast, reliable services used by mobile and desktop apps.

You will work on latency, scalability, and observability while collaborating with AI/ML teams to bring new capabilities into production.