AI Backend Engineer: Proactive, Low-Latency AI Systems

ActAI; Palo Alto (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

ActAI is building a next-generation platform for AI-powered interactions and workflows. The Backend Engineer, AI, will own the inference and orchestration layer that powers every AI interaction in the product, sitting between models and users.

You will design, build, and operate production systems that deliver fast, stable, and observable APIs used across mobile and desktop clients. Your work will focus on multi-step AI workflows, tool calls, retries, and cost optimization, collaborating with ML

Qualifications

• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns (LLMs, embeddings).
• Bias toward shipping and learning from production behavior.

Responsibilities

• Build and operate production systems for AI interactions.
• Design inference pipelines and orchestration for multi-step workflows.
• Manage routing, caching, batching, streaming, state management.
• Optimize latency, throughput, cost across model inference.
• Ensure reliability despite non-deterministic model behavior.
• Implement observability: logging, tracing, debugging.

Skills

High-throughput services

Low-latency systems

AI inference patterns

Observability

Tools

Python

Node.js

PyTorch

OpenAI LLMs

Docker

SQL/NoSQL

Job description

ActAI is building a next-generation platform for AI-powered interactions and workflows. The Backend Engineer, AI, will own the inference and orchestration layer that powers every AI interaction in the product, sitting between models and users.

You will design, build, and operate production systems that deliver fast, stable, and observable APIs used across mobile and desktop clients. Your work will focus on multi-step AI workflows, tool calls, retries, and cost optimization, collaborating with ML