Full Stack Engineer

A little about us… 

Knit is the AI-native consumer research platform helping brands automate and accelerate primary research. With our Researcher-Driven AI, we’ve condensed the entire quant + qual research process from weeks into days (sometimes hours!) for 50+ enterprise brands — including Amazon, T-Mobile, Mars, NASCAR, and more. We’re on a mission to scale and democratize world-class research. From survey generation to stakeholder-ready reports, our platform is redefining how insights teams operate — and we need your help to push the limits of what’s possible.

Overview

We’re continuing to build out our NYC engineering team and are looking for exceptional builders who are resourceful, deeply technical, and thrive in high-ownership environments.

As an early member of the team, you’ll play a key role in shaping the core of our platform and contributing to a team that will scale to 20+ engineers over the next 18 months. You’ll build and orchestrate AI agents, explore new UX paradigms, and work on some of the hardest problems in applied AI with meaningful ownership across the stack.

**Responsibilities | What you will own...

**

Primary responsibilities of this role:

• Own 0→1 and 1→N features across the stack, from design docs to building high-throughput data pipelines and scalable FastAPI services.
• Architect and own the core agent orchestration engine, designing complex, multi‑agent LLM workflows (routing, tool‑use, memory, evaluation) with deterministic fallbacks, guardrails, and auditable actions required by enterprise users.
• Build AI‑native, human‑in‑the‑loop UIs. Craft React/Next.js interfaces that let users collaborate safely with agents, with transparency and explainability by design.
• Develop the "factory for the factory". Build our experimentation platform: CI/CD for prompts and agents, offline/online evals, drift detection, safety layers, and rollout controls.
• Ship fast, safely. You’ll instrument everything for reliability, write concise design docs, add robust tests, and build dashboards and alerts for features you launch.
• Partner cross‑functionally with Product, AI, Design, CS; talk to customers and SMEs, and turn ambiguous problems into shipped product.
• Obsess over performance, optimizing for latency across the system: caching, model selection, distillation, batching, vector search, and infrastructure efficiency (GPU/CPU).
• Operate what you build. This includes on‑call ownership, leading incident response, and driving learning through blameless postmortems.