[Hiring] Senior AI Engineer @Instrument

Role Description

As a member of our freelance network, you’ll collaborate with our teams to bring bold ideas to life—whether launching new brands, building digital products, or shaping experiences that move people. We welcome collaborators from all backgrounds and experiences who share our curiosity, creativity, and care for craft.

The Project involves developing a highly complex, stateful, multi-agent simulation engine driven by generative AI. This greenfield project explores new forms of non-linear, narrative-based user interaction at scale, requiring persistent "memory" for thousands of unique, evolving user sessions.

The Role of Sr. AI Engineer focuses on the core intelligence and agentic logic that drives the application. Responsibilities include:

• Designing the multi-agent architecture that manages core interactive loops, dynamic scenario generation, and global system state aggregation.
• Ensuring agents are fast, reliable, and strictly scoped to minimize latency and hallucination.

This is a part-time contract role (20 hrs/week) from 4/13–5/29, with a strong likelihood of extension through October at full-time hours.

Qualifications

• Strong traditional programming background.
• 1–3 years of deep, hands-on experience building and deploying LLM-backed applications in production.
• Strong proficiency in Python.
• Strong proficiency in TypeScript and familiarity with modern reactive frontend frameworks (preferably Angular v21).
• Hands-on experience with modern agent harnesses (e.g., LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK, Google ADK).
• Deep understanding of how LLMs process information.
• Hands-on experience with designing and employing guardrails for agents’ actions and outputs.

Requirements

• Build and manage the logic for complex multi-agent workflows.
• Architect state management for the LLMs to prevent "context rot" and hallucination.
• Write, test, and version-control robust system instructions for standalone LLMs and multi-agent workflows.
• Design and implement pipelines that moderate harmful or offensive user inputs.
• Work closely with backend and frontend teams to integrate AI outputs into the user interface.

Benefits

• The expected pay range for this role is $61 - $78 per hour based on the US 3 pay range for a W-2 temporary engagement.
• Regional pay bands based on location: US 1, US 2, and US 3.
• US 2 pay is 7.5% higher than US 3; US 1 pay is 15% higher than US 3.