Genesis is looking for an ML Prompt Engineer to be a key part of our AI team. You will develop the core intelligence of our product—a sophisticated system of prompts, RAG pipelines, and AI logic that defines the effectiveness of all functions. This role focuses on building chain-of-thought mechanics, optimizing prompts, and improving model stability.
What You'll Do
- Create and optimize prompts of varying complexity for generation, reasoning, QA, and classification.
- Build chain-of-thought logic and develop agent-based workflows.
- Develop multimodal and multi-LLM pipelines.
- Work with RAG systems including embeddings, retrieval, chunking, and contextual structures.
- Analyze answer quality, build metrics, and conduct systematic tests.
- Reduce hallucination rates and improve overall model stability.
- Research and integrate new models from providers like OpenAI, Anthropic, Mistral, and Llama.
- Create comprehensive documentation, including guides, standards, and prompt flows.
- Collaborate with ML Engineers on production integration.
- Optimize token costs, model selection, and system prompts.
What We're Looking For
- 1+ years of experience with LLMs in a Prompt Engineer or AI Specialist role, OR 2+ years in Data, Product, ML, or NLP.
- Deep understanding of LLM principles and mechanics.
- Hands-on experience with OpenAI API, Anthropic, Mistral, and HuggingFace.
- Understanding of RAG approaches and experience working with vector stores.
- Ability to work with JSON/YAML and manage complex prompt structures.
- Basic Python skills for writing tests and integrations.
- High attention to detail and strong logical thinking.
- Comfort with a fast pace and the dynamic atmosphere of a product startup.
- A genuine, deep interest in AI technology.
Nice to Have
- Advanced Python knowledge.
- Experience building RAG systems from the ground up.
- Knowledge of evaluation frameworks like Evals, Ragas, or Argilla.
- Understanding of guardrails and moderation systems.
- Experience with LangChain or LlamaIndex.
Technical Stack
- LLMs & APIs: OpenAI API, Anthropic, Mistral, Llama, HuggingFace
- Languages & Formats: Python, JSON/YAML
- Core Concepts: RAG
- Frameworks & Tools: LangChain, LlamaIndex, Evals, Ragas, Argilla
Team & Environment
You will be a key part of the AI team, working in a structure with high trust and minimal bureaucracy.
Benefits & Compensation
- Opportunity to build product AI architecture from scratch.
- Work with the latest models and infrastructure.
- Direct influence on the strategic development of AI components.
- Learning opportunities, conference support, and professional growth.
- Remote work format.
- A team without bureaucracy, characterized by high pace and trust.
- A product operating on the international market.
Work Mode
This is a fully remote position.
Genesis is an equal opportunity employer.
