Senior AI Engineer: Real-Time Inference & Agent Systems

Arcana Analytics; United States; On-site; USD 120,000 - 160,000; Full time

Job summary

Arcana Analytics is seeking a Senior AI Engineer specialized in Inference & Agent Systems. This role focuses on optimizing AI agents to deliver rapid, accurate information synthesis from diverse data sources.

The ideal candidate will have experience building high-performance inference systems in production environments, with a focus on streaming LLM responses and managing latency challenges.

Joining us means tackling genuinely unsolved problems with a small, dedicated team, where every decision impacts production outcomes.

Qualifications

• Experience building AI systems in production at scale.
• Understanding of latency requirements and performance optimization.
• Capability to build and maintain inference pipelines.

Responsibilities

• Optimize multi-step agent pipelines to meet strict latency targets.
• Design and implement orchestration and evaluation frameworks.
• Handle debugging and non-deterministic LLM behaviors.

Skills

Inference optimization

Streaming LLM responses

Multi-step agent systems

Debugging LLM non-determinism

Tools

Go

Python

Temporal

PostgreSQL

Docker

Job description

Arcana Analytics is seeking a Senior AI Engineer specialized in Inference & Agent Systems. This role focuses on optimizing AI agents to deliver rapid, accurate information synthesis from diverse data sources.

The ideal candidate will have experience building high-performance inference systems in production environments, with a focus on streaming LLM responses and managing latency challenges.

Joining us means tackling genuinely unsolved problems with a small, dedicated team, where every decision impacts production outcomes.