AI Engineer - Application Design & Rapid Deployment

AI Engineer (Application Design & Rapid Deployment)

Role Overview

As an AI Engineer, you will serve as one of our "Tiger Team" engineers:  a highly versatile, full-stack application specialist who designs, builds, and deploys high-impact AI applications from end to end. You excel at taking a vague business problem and turning it into a production-ready AI solution in record time. Leveraging expertise in advanced orchestration frameworks like LangGraph and cutting-edge developer tools like Claude Code, you will act as the primary designer of our user-facing AI applications.

Beyond execution, you will play a vital role as an organizational enabler. You will build the evaluation systems necessary to guarantee model performance, integrate AI capabilities into workflows safely and effectively.

Key Responsibilities

AI Application Design & Rapid Execution

• End-to-End Application Design: Serve as designer and builder for new AI applications, mapping out how the user interface, backend logic, and AI agents interact.

• Advanced Agentic Workflows: Build complex, stateful, multi-agent systems and cyclic workflows using LangGraph inside and out to handle sophisticated enterprise use cases.

• Rapid Prototyping: Utilize full-stack capabilities and AI-assisted development tools (e.g., Claude Code) to build high-fidelity minimum viable products (MVPs) at an accelerated pace.

Evaluation & Quality Assurance

• LLM Evaluation Tools: Design, build, and maintain automated testing and evaluation frameworks (e.g., Ragas, TruLens, or custom LLM-as-a-judge pipelines) to measure accuracy, latency, hallucinations, and regression across applications.

• Framework Stress-Testing: Act as power-user of our internal AI Development Framework, enabling its capabilities in real-world scenarios and providing direct feedback to the core architecture team.

Qualifications & Skills

Experience

• Industry Tenure: 5+ years of professional full-stack software development experience.

• AI Engineering Specialization: Proven track record of designing and deploying production-grade LLM applications, with a heavy emphasis on multi-agent architectures.

• The "Tiger Team" Mindset: Experience thriving in fast-paced, high-agility environments where requirements evolve rapidly and execution speed is critical.

Technical Skills

• Orchestration Mastery: Deep, production-level expertise with LangGraph for building stateful, multi-agent workflows, alongside standard libraries.

• AI Tooling & Full-Stack Stack: Hands-on mastery of Claude Code for accelerated development, combined with robust backend skills (Python, Node.js) and modern frontend frameworks (React/Next.js).

• AI Evaluation & MLOps: Strong understanding of LLM evaluation methodologies, dataset curation for testing, and semantic logging/tracing tools (e.g., LangSmith).

• Data Layer: Proficient with vector databases (e.g., Pinecone, Qdrant, Milvus), relational databases, and integrating unstructured data pipelines.

• Prompt Engineering: Excellent at prompt engineering best practices and with good linguistic intuition for LLM best performance.

Soft Skills & Leadership

• Excellent communication and collaboration skills.

• Self-driven and eager to mentor and share knowledge.

• strong product sense; the ability to balance complex AI logic with intuitive user experiences and immediate business value.

• A self-starter who can own an application from a blank text document to a live production URL with minimal supervision.