LLM Product Engineer - Agents & Features (NYC, Onsite)

Digital Waffle; New York (NY); On-site; USD 140,000 - 200,000; Full time

Benefits offered by this job

In-office in New York

Competitive compensation

Job summary

Digital Waffle in New York is seeking an AI Engineer to design, build and ship LLM-powered product features and agentic workflows into production. This is a hands-on, build-focused role working alongside product and users, not a pure research position.

You will work with Python and TypeScript, handle tool calling, RAG, vector search and eval pipelines, integrate with React/Next.js surfaces, and own AI layer metrics like cost, latency and reliability while collaborating closely with model

Qualifications

• Production experience shipping LLM-powered features.
• Strong Python and TypeScript in production.
• Familiarity with tool calling, RAG and vector databases.

Responsibilities

• Design and ship production LLM features and agents.
• Build the applied AI toolkit end to end (tool calling, RAG, vector search).
• Work with model APIs (Anthropic, OpenAI, Google) and open-source models as suitable.
• Build evaluation pipelines to measure quality.
• Integrate agents into React/Next.js product surfaces.
• Own AI layer cost, latency and reliability.

Skills

Python

TypeScript

LLM features

Production experience

API integration

Tools

Anthropic API

OpenAI API

LangSmith

Vector databases

Job description

Digital Waffle in New York is seeking an AI Engineer to design, build and ship LLM-powered product features and agentic workflows into production. This is a hands-on, build-focused role working alongside product and users, not a pure research position.

You will work with Python and TypeScript, handle tool calling, RAG, vector search and eval pipelines, integrate with React/Next.js surfaces, and own AI layer metrics like cost, latency and reliability while collaborating closely with model