ABOUT THE ROLE
We build domain-specific, context-aware AI assistants powered by Large Language Models and agentic AI. Our assistants go well beyond a chatbot:
they interpret what a user is actually asking, decide which tools and data sources are needed, orchestrate multiple specialized agents and steps to
carry out the work, and compose a clear answer grounded in real data.
In practice that means LLM-driven reasoning wired into real systems- tool and function calling, workflow and agent orchestration, conversation memory,
and autonomous multi-step execution - delivered across web and mobile, in both text and voice.
This is a senior role to design, enhance, and own one of these products in production. You'll own meaningful parts of a live AI system building new
capabilities, expanding what it can handle, deepening how it understands a conversation, and integrating it with more tools, data, and agents. This is a build-and-grow role on a system already in production, not a research project.
You'll work closely with product and data teams, take genuine ownership, and see your work reach users quickly.
WHAT YOU'LL DO
• Design and build new capabilities for the assistant - from idea to production.
• Build the agentic core: LLM-driven reasoning that decides what to do, calls the right tools, and runs multi-step workflows.
• Design how multiple specialized agents and steps coordinate to handle complex requests (agentic orchestration).
• Integrate the assistant with data sources, internal APIs, and external tools through function/tool calling.
• Build and refine conversation memory and context handling, so it follows up naturally across a chat.
• Expand the range of questions it can handle and the depth of its answers.
• Keep answers grounded in real data - a principle we build to.
• Improve the speed, cost, and stability of the system as it scales.
• Use evaluation and monitoring to keep quality high as the product grows.
• Deploy, monitor, and support the assistant in production.
• Partner with product owners and stakeholders to turn business needs into working features.
WHAT WE'RE LOOKING FOR
• 5+ years building backend systems in Python (FastAPI, Django, or Flask).
• Real hands-on experience building applications with LLMs — production, not just prototypes.
• Hands-on experience designing agentic systems: tool/function calling, workflow orchestration, and multi-agent coordination.
• A good grasp of prompt design, conversation memory, and context management.
• Familiarity with retrieval and semantic search (embeddings, vector databases) and a sense of when to use them.
• Familiarity with an agent/orchestration framework (LangChain, LlamaIndex, LangGraph, or similar).
• Experience running APIs and services in production on a major cloud (AWS, Azure, or GCP).
• A strong ownership mindset - able to drive a feature from design to production with limited hand-holding.
• A clear communicator who's comfortable working directly with product people and stakeholders.
NICE TO HAVE
• Experience building AI on top of large, real-world datasets.
• Exposure to voice or conversational interfaces.
• Experience with .NET / ASP.NET Core (part of our stack uses it).
WHY THIS ROLE
• Work on a live, agent-driven AI product with real users - not a proof-of-concept.
• Real ownership and fast impact - what you build ships.
• A role where quality and craft genuinely matter.
We collect personal data necessary for recruitment and employment purposes, including but not limited to:
The personal data we collect is used for the following purposes:
We may share your information with:
We implement strict security measures including:
Your data will be retained as long as necessary for the recruitment process. Unsuccessful applications may be kept for future opportunities unless deletion is requested.
Contact us at hr@weybee.com for any privacy concerns.