AI Engineer

Digital Waffle; New York (NY); On-site; USD 120,000 - 200,000; Full time

Job summary

Digital Waffle in New York is seeking an AI Engineer to design, build and ship LLM-powered features and agentic workflows.

You will work on the applied AI stack—prompts, retrieval, tools, agents, evals—and connect them to a real product, collaborating closely with product and users. This role requires hands-on production experience and a bias for shipping.

Qualifications

• Strong production experience shipping LLM-powered features.
• Practical grasp of the applied AI stack: function calling, RAG, vector databases, structured output.
• Experience building evals and guardrails for LLM output.

Responsibilities

• Design and ship production LLM features and agents using Python and TypeScript.
• Build the applied AI toolkit end to end: tool and function calling, RAG, vector search, structured output, prompt management, context handling.
• Work directly with foundation model APIs (Anthropic, OpenAI, Google) and open-source models where it makes sense.
• Build evaluation pipelines so quality is measurable rather than anecdotal.
• Integrate agents into existing product surfaces built in React and Next.js.
• Own cost, latency and reliability of the AI layer as first-class concerns.
• Use AI tooling across your workflow to compress the build cycle.

Skills

Python

TypeScript

LLM features

API design

Backend engineering

Evaluation pipelines

Guardrails

Agent frameworks

Job description

A high-growth AI-native startup is hiring an AI Engineer in New York to design, build and ship LLM-powered product features and agentic workflows into production.

This is a build role focused on the applied AI stack: prompts, retrieval, tools, agents, evals and the glue that connects them to a real product. You’ll work close to product and real users, not inside a research lab.

Location: New York, 5 days per week in office

What you’ll be doing:

• Design and ship production LLM features and agents using Python and TypeScript
• Build the applied AI toolkit end to end: tool and function calling, RAG, vector search, structured output, prompt management, context handling
• Work directly with foundation model APIs (Anthropic, OpenAI, Google) and open-source models where it makes sense
• Build evaluation pipelines (Braintrust, LangSmith or custom) so quality is measurable rather than anecdotal
• Integrate agents into existing product surfaces built in React and Next.js
• Own cost, latency and reliability of the AI layer as first-class concerns
• Use AI tooling (Claude, Cursor and similar) across your workflow to compress the build cycle

What you’ll need:

• Strong Python and TypeScript, with real production experience shipping LLM-powered features
• Practical grasp of the applied AI stack: function calling, RAG, vector databases, structured output, prompt engineering, context management
• Comfort with at least one agent framework or SDK, with a view on why the abstractions exist
• Experience building evals and guardrails for LLM output
• Solid API, integration and backend engineering fundamentals
• Fluent in modern AI engineering tools and able to use them to raise output
• Happy working 5 days a week in-person with a small, high-intensity team

Nice to have:

• Prior work on agentic systems in production (not just prototypes)
• Experience with multimodal models (vision, audio, video)
• Exposure to fine-tuning or post-training of foundation models

This role would suit an AI engineer who wants to ship real LLM product into users’ hands, not write another whitepaper.