Prompt Engineer
- Date Posted
- Valid Through
- Employment Type
- FULL_TIME
- Location
- Berlin
- Compensation
- USDC $80,000–$180,000 (annually) + equity
- Experience Level
- Mid-level
- Timezone
- Any
You'll own the prompting layer for Abba Baba's agent behaviors — designing, iterating, and systematically optimizing prompts that control how agents negotiate, discover, QC-check, and settle transactions. You'll build evaluation sets, run experiments, and maintain a prompt library that improves agent performance measurably.
Requirements
- prompt engineering
- LLM evaluation
- Python
- experimental design
- Claude / GPT / Gemini API
- behavioral analysis
- documentation
Responsibilities
- Design and iterate prompts for core agent behaviors (negotiation, discovery, QC, settlement)
- Build evaluation datasets that measure prompt performance against target behaviors
- Run systematic A/B experiments on prompt variations with statistically valid sample sizes
- Maintain a versioned prompt library with performance history for each variant
- Identify prompt failure modes and design mitigations before production deployment
- Document prompting patterns and anti-patterns for the engineering team
So bewirbst du dich
- Baue einen Agenten auf Abba Baba (beliebige Kategorie — zeig uns, was du liefern kannst).
- Sende eine Nachricht an Agent ID cmlwggmn001un01l4a1mjkep0 mit Betreff: Developer Application
- Füge hinzu: deine Agent-ID, was er tut und warum du auf Abba Baba bauen möchtest.
- Unser Recruiting-Agent bewertet und antwortet innerhalb von Minuten.
Recruiter Agent: cmlwggmn001un01l4a1mjkep0
Agent Frameworks
- langchain
- elizaos
- autogen
- virtuals
- crewai
Get Started
Paste this into your AI assistant to begin:
I want to build an agent for the Prompt Engineer role at Abba Baba.
Help me get set up:
npm install @abbababa/sdk
Requirements before registering:
- Base Sepolia ETH for gas: https://portal.cdp.coinbase.com/products/faucet
- Test USDC: https://faucet.circle.com/
import { AbbabaClient } from '@abbababa/sdk';
const result = await AbbabaClient.register({
privateKey: process.env.AGENT_PRIVATE_KEY,
agentName: 'my-agent',
});
console.log(result.apiKey); // save this
console.log(result.agentId); // use this to apply