Agent Engineer San Francisco CA

AHU Technologies Inc; Washington (District of Columbia); On-site; USD 120,000 - 150,000; Full time

Job summary

AHU Technologies Inc in Washington is seeking an experienced Agent Engineer to build and scale AI agent workflows for a creative platform. Candidates must have experience with LLMs, AI agents, backend systems, and production-grade AI applications.

This position requires a strong understanding of Python or TypeScript, along with 3 years of experience in AI-related roles. The job is onsite in San Francisco, CA.

Qualifications

• 3+ years of experience in AI, backend, infrastructure, or agent-based systems.
• Strong Python and/or TypeScript experience is required.
• Experience with LLMs, AI agents, and production systems.

Responsibilities

• Build and scale AI agent workflows for a creative platform.
• Collaborate with teams to develop AI applications.
• Implement model orchestration and memory retrieval.

Skills

Python

TypeScript

AI systems

DevOps

Workflow orchestration

Job description

Position: Agent Engineer

Location: San Francisco, CA (Onsite)

Job Type: Full-Time

Job Summary

We are seeking an experienced Agent Engineer to build and scale AI agent workflows for a creative platform. The ideal candidate will have experience with LLMs, AI agents, backend systems, workflow orchestration, and production‑grade AI applications.

Requirements

• 3+ years of experience in AI, backend, infrastructure, or agent‑based systems
• Strong Python and/or TypeScript experience
• Experience with LLMs, AI agents, tool use, memory, retrieval, and workflow execution
• Experience with databases, queues, observability, and production systems
• Knowledge of model orchestration, routing, retries, fallbacks, and reliability
• Experience with AI evaluations, testing, and quality metrics
• Ability to work on‑site in San Francisco

Preferred Qualifications

• Experience with image, video, audio, or multimodal AI systems
• Experience with workflow engines, node‑based systems, or automation platforms
• Strong understanding of production AI reliability and scalability