Founding Harness Engineer

Heyjared; Polska; Hybrid; PLN 777,000 - 1,166,000; Full time

Job summary

Heyjared is seeking a Founding Harness Engineer for Eastern Europe. You will build the harness that enables Jared's AI coworker to act as a proactive, careful teammate, managing context, tools, and approval gates.

You will ship production-ready agents, design system prompts, and craft robust evaluation harnesses while collaborating with the founder and early users from Serbia, Poland or other Eastern European countries.

Qualifications

• Shipped agents that use tools in production.
• Hands-on system prompt design improved through testing.
• Strong regression/eval harness experience.
• Understanding safe tool execution and data risk.
• Ability to own broad problems from prototype to production.

Responsibilities

• Design and build the agent runtime: how Jared gets context, decides when to speak, chooses tools, waits for approval, completes work.
• Write and iterate system prompts: proactive without noisy or reckless
• Build eval and regression tests around real tasks, tool use, failure cases. Prompt changes are code: test them, catch regressions
• Make behaviour reliable across long-running work, interruptions, retries
• Build safe boundaries: approval gates, multi-tenant data separation
• Work directly with the founder and early users

Skills

Agent development

Tool integration

System prompts design

Regression testing

Safety & data risk

Prototype to production

Founding team mindset

Tools

Production tools

Job description

Founding Harness Engineer - Eastern Europe

Jared - Hire an A[I] Player

Location: Remote from Serbia, Poland and other Eastern European countries. Local employment or contractor structure and working-hour overlap to be confirmed.

Compensation: $200,000-$300,000 annual cash compensation in USD plus equity.

Equity percentage, vesting and (where applicable) commission plan require confirmation. OTE is not guaranteed base pay.

Jared is an AI coworker for teams. You'll build the harness that makes it act like a useful teammate: proactive when it should be, careful when an action needs approval, dependable enough for real work.

What you'll do:

• Design and build the agent runtime: how Jared gets context, decides when to speak, chooses tools, waits for approval, completes work
• Write and iterate system prompts: proactive without noisy or reckless
• Build eval and regression tests around real tasks, tool use, failure cases. Prompt changes are code: test them, catch regressions
• Make behaviour reliable across long-running work, interruptions, retries
• Build safe boundaries: approval gates, multi-tenant data separation
• Work directly with the founder and early users

What we're looking for:

• Shipped agents that use tools in production, not demos or prompt wrappers
• Knows how to get an agent to take useful initiative, and when it should act, ask, or stay quiet
• Hands-on system prompt design improved through testing
• Strong regression/eval harness experience
• Understands safe tool execution, approval gates, multi-user data risk
• Owns broad problems prototype to production, explains tradeoffs
• Wants a founding role working remotely from Serbia, Poland or another Eastern European country