Fetcherr experts in deep learning, e-commerce, and digitization, Fetcherr disrupts traditional systems with its cutting-edge AI technology. At its core is the Large Market Model (LMM), an adaptable AI engine that forecasts demand and market trends with precision, empowering real-time decision-making. Specializing initially in the airline industry, Fetcherr aims to revolutionize industries with dynamic AI-driven solutions.

We are seeking an experienced LLM (AI) Architect to lead the design and implementation of a production-grade, LLM-powered question-answering and graph plotting system that allows users to interact with complex internal data using natural language.

You will not train foundation models—but instead orchestrate LLM-powered architectures (e.g. using OpenAI, Claude, Gemini, etc.), focused on retrieval-augmented generation (RAG), prompt engineering, and context-aware querying across structured and unstructured internal data sources.

Responsibilities

LLM-Powered System Design

• Design and build systems that let users query internal data using natural language, simulating an AI analyst.
• Create robust pipelines that use LLMs + internal structured/unstructured data to provide accurate and explainable responses.
• Architect and optimize RAG systems
  
  

Prompt Engineering & Tooling

• Develop advanced prompt strategies for dynamic querying, chaining, and task delegation.
• Implement fallback strategies, guardrails, and context control for reliability and consistency.
• Tune prompts and system behavior to balance accuracy, latency, and cost.
  
  

Infrastructure & Deployment

• Work with data engineers and MLOps to deploy and scale LLM-based services in production.
• Integrate vector databases, embedding pipelines, and caching layers to optimize performance.
• Ensure systems are monitored, observable, and cost-aware.
  
  

Collaboration & Productization

• Partner with product managers and analysts to define use cases and measure business impact.
• Translate user needs and business logic into scalable LLM-powered applications.
• Educate internal teams on the capabilities and limitations of LLMs in the company context.
  
  

Requirements:

You'll be a great fit if you have…

• 5+ years of experience in machine learning, AI engineering, or backend systems.
• 2+ years working specifically with LLM architectures or generative AI applications.
• Hands-on experience with:
• RAG frameworks (LangChain, LlamaIndex, etc.)
• Embedding models and pipelines
• LLM APIs (OpenAI, Claude, Gemini, etc.)
• Strong Python skills and familiarity with cloud infrastructure (GCP preferred).
• Proven track record building reliable, production-grade AI systems.
• Fluent in English (spoken and written) for documentation and cross-team collaboration.
  
  

Mindset & Approach

• Deeply product-oriented with a strong user empathy.
• Balances experimentation with engineering discipline.
• Collaborative, hands-on, and outcome-driven.
  
  

Nice to Have:

• Experience in analytics, BI, or data exploration interfaces.
• Familiarity with semantic search, question decomposition, and tool-augmented LLMs.
• Background in pricing, forecasting, or airline data domains.