Job Description

Title: Applied AI Engineer / Developer (Claude + Python)
Type: Full-Time | In-Office | Growth Opportunity

About Us

We’re building a small, fast-moving team focused on practical AI agents that actually help people get real work done. You’ll work at the intersection of Claude, Python, and modern product design—creating and integrating AI agents into internal tools, customer-facing experiences, and creative workflows.

This is a full-time, on-site role (not remote), ideal for someone who has been experimenting with LLMs and is ready to take ownership of end-to-end AI projects in a collaborative, hands-on environment.

As an Applied AI Engineer / Developer, you will design, build, and refine AI agents powered by Claude and other LLMs, integrate them with Python back-ends and third-party APIs, and partner closely with designers and business stakeholders.

You’ll own projects from concept through production—scoping requirements, prototyping, iterating on prompts and architecture, and delivering reliable, maintainable solutions—while also collaborating closely with the rest of the team to share patterns and improve our overall AI stack.

What You’ll Do

• Architect, implement, and maintain Claude-powered workflows and agents using Python.
• Call LLM APIs (Claude and others), parse responses, and integrate them into internal tools, web applications, and operational workflows.
• Design and build integrations with external tools, REST APIs, databases, and other services to make agents genuinely useful in real-world work.
• Lead prompt design and iteration—testing prompts, contexts, and settings to improve reliability, quality, and user experience.
• Build and optimize context-augmented / RAG-style workflows (feeding documents or data into LLMs in a controlled, auditable way).
• Write clean, testable Python code with appropriate logging, error handling, and basic observability.
• Collaborate with designers, product, and non-technical stakeholders to turn ideas into scoped, deliverable AI-powered features and tools.
• Take ownership of projects end-to-end: requirements gathering, technical design, implementation, handoff, and ongoing improvement.

What We’re Looking For

• 2–4+ years of programming experience (professional, internship, or substantial project work) with strong Python skills.
• Hands-on experience with large language models (Claude, ChatGPT, Gemini, etc.)—through production use, projects, coursework, or serious personal experimentation.
• Experience calling web APIs (REST/JSON) and working with JSON data in Python.
• Familiarity with core LLM concepts: prompts, tokens, context windows, and issues like hallucinations and guardrails.
• Comfort using Git and working in a collaborative development workflow (code reviews, branching strategies, etc.).
• Ability to balance autonomy and collaboration: you can drive a project forward independently while communicating clearly and syncing with the team.
• Strong problem-solving skills, curiosity, and a bias toward experimentation and continuous improvement.
• Ability and willingness to work on-site full time at our office location (this is not a remote or hybrid role).

Nice to Have

• Direct experience with Claude (Claude API, Anthropic console, or Claude-based tools).
• Projects involving chatbots, assistants, AI agents, or workflow automation that solved a real user or business problem.
• Exposure to web frameworks (FastAPI, Flask, or a front-end framework like React/Next.js).
• Experience partnering with designers, content teams, or UX to ship polished user-facing experiences.
• Working knowledge of vector databases, embeddings, or RAG-style systems, and how they fit into production AI architectures.
• Basic familiarity with observability and deployment practices for AI-powered systems (e.g., monitoring, logging, error tracking).

What We Offer

• Full-time, on-site position with weekly pay.
• Competitive compensation and benefits (health, PTO, etc.).
• A collaborative environment that encourages ownership, experimentation, and cross-functional learning.
• Direct mentorship and peer support from experienced AI/LLM practitioners on real-world projects.
• The opportunity to work hands-on with the latest LLM tools and workflows, shape our AI capabilities, and grow quickly as the team and company expand.

How to Apply

Please send your resume, a brief introduction, and links to any relevant projects (GitHub, portfolio, or demos). If you’ve built anything with LLMs—even internal tools or small experiments—highlight those. We’re especially interested in how you think, design, build, and learn, and in examples where you owned a project from start to finish..