AI Engineer-Hermes Agent
Summary
Design, build, and orchestrate autonomous AI agents using the Hermes Agent framework — implementing reasoning patterns (ReAct, CoT, ToT), vector-DB memory and RAG, tool/API integrations, and production observability and evaluation. The role is hands-on Python LLM engineering based in Weimar with remote flag set.
Compensation: No equity
About the Role:
We are seeking a forward-thinking Agentic AI Engineer to design, build, and orchestrate autonomous AI agents capable of reasoning, planning, and executing complex workflows. Unlike traditional LLM-based chatbots, our agents interact with dynamic environments, use tools, collaborate with other agents, and operate with minimal human intervention.
Agent Architecture & Development:
Framework: Hermes Agent Collaboration: orchestrator-workers, debate, hierarchical swarms Memory: short/long-term + episodic via vector DBs & semantic caching
Reasoning & Planning: Techniques: ReAct, CoT, ToT, Plan-and-Solve Dynamic planning, error recovery, replanning from feedback Tool use: function calling, API grounding (DBs, APIs, RAG, UI automation)
Production & Evaluation: Eval: agentic evals for task completion, efficiency, safety (not just lexical) Observability: tracing/logging (LangSmith, Arize, W&B) Optimize: latency, token cost, reliability
Integration & Tooling: Connect: CRMs, DBs, Slack, browsers, REST APIs, code interpreters Custom tools + sandboxed envs for safe code/shell execution
Technical Skills:
- Programming: Expert in Python
- Strong understanding of prompt engineering, few-shot learning, and structured output generation (JSON mode, grammars).
- Reasoning Patterns: Proven experience implementing agentic patterns (ReAct, Reflexion, Toolformer) in production or complex prototypes.
- Memory & Retrieval: Experience with vector databases (Pinecone, Weaviate, Qdrant) and RAG optimization (hybrid search, reranking).
- Orchestration: Familiarity with workflow engines (Temporal, Prefect, Airflow) for human-in-the-loop and durable execution.
- Observability: Experience monitoring LLM applications (prompt traces, token usage, drift).
- Model Context Protocol: Built agents that use MCP for multi-step research, code analysis, or data engineering tasks.
- Agentic Framework : Practical experience with Hermes Agent
Education & Experience:
- Bachelor’s degree in Computer Science, Software Engineering, AI, or related discipline
- 5 years in software engineering
- Strong background on Spec-Driven Development ( SDD ) methodology
- Practical experience installing, configuring, and operating Hermes Agent (the self-improving AI agent framework from Nous Research)
- Experience building production-grade agentic systems (not just demos or chatbots).
- Must be well versed with any of the following Method:
- BMAD ( Breakthrough Method for Agile AI-Driven Development )
- Github Spec Kit
- OpenSec
- Strong understanding of LLM limitations: hallucinations, jailbreaks, prompt injection, and failure modes.
- Good understanding of MCP discovery patterns and context negotiation.
- Strong knowledge of context management in LLM applications: prompt caching, sliding window, semantic retrieval, MCP resource lifecycle.