A

AI Harness Engineer – Founding AI Team

Visa Sponsorship
Apply Now

Build and maintain the core agent runtime and orchestration framework for an AI platform integrating chemistry systems. Focus on state management, reliability, and production-grade agent infrastructure. Requires 2+ years of experience in agent harnesses, Python, and systems engineering.

Key Responsibilities
Design, build, and maintain the core agent runtime and orchestration framework
Develop execution graphs, tool contracts, state management, and multi-step agent workflows
Integrate external tools and systems (retrosynthesis engines, reaction databases, simulation packages, laboratory systems)
Build reliable systems for long-running workflows, retries, checkpoints, and recovery
Develop evaluation frameworks, tracing, and regression suites for agent performance measurement
Improve production reliability, observability, and execution efficiency
Build rollout and trajectory infrastructure for reinforcement learning and model post-training
Technical Skills Required
Python Agent Orchestration Systems Engineering
Benefits & Perks
$200,000–$300,000 base salary
Meaningful equity
Visa sponsorship for H-1B, O-1, and TN
Competitive early-hire equity package
Nice to Have
Experience with frameworks like LangGraph, AutoGen, DSPy, Temporal, or CrewAI
Background in RL environments, rollout, or trajectory pipelines
Experience integrating scientific tools or complex enterprise systems
Open-source contributions or publications related to agent infrastructure
Track record of improving measurable production reliability through evaluation systems

Job Description

As an AI Harness Engineer, you will build and own the agent harness at the heart of the company's AI platform. Responsibilities include designing the core agent runtime and orchestration framework, developing execution graphs, tool contracts, state management, and multi-step agent workflows.

You will integrate external tools like retrosynthesis engines, reaction databases, simulation packages, and laboratory systems. Build reliable systems for long-running workflows, including retries, checkpoints, and recovery. Develop evaluation frameworks, tracing, and regression suites to measure real-world agent performance.

Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources
Keep exploring

Similar Jobs

Explore other opportunities that match your interests

Hidden company

Log in to see location

Premium

Cloud Infrastructure Engineer

Log in free to see the details

Hidden company

Log in to see location

Premium

Financial Product Engineer

Log in free to see the details

Visas, Work Permits & Legal Insights

Stay informed about visa types, work permits, and immigration updates for international professionals.

Browse all articles

Subscribe to our newsletter

New visa sponsorship, relocation and remote tech jobs, delivered to your inbox.