Backend Engineer

DevHub

New York (NY)

On-site

USD 150,000 - 250,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Healthcare (employer-paid)

Unlimited vacation

Equinox membership

Office meals

Job summary

Guac is building AI-native tools to forecast grocery demand and optimize inventory for retailers. As a Backend Engineer in NYC, you’ll own technical decisions, design robust backend services, and ship data-heavy pipelines powering ordering and production planning products.

You will work hands-on with LLMs, tool-use and AI-native tooling, collaborating with customers’ tech teams to integrate with their IT infrastructure.

Qualifications

3+ years of relevant software engineering experience.

Responsibilities

Design and build robust backend services that power mission‑critical ordering and production planning products.
Build efficient ETL pipelines to handle billions of rows of data, multiple times per day.
Build AI‑powered tools and agents for internal and customer use — exposing our data and forecasting systems via MCP servers, tool‑use APIs, and similar protocols so that LLMs can reason over and act on grocery operations data
Collaborate directly with customers’ technical teams to understand and integrate with their IT infrastructure
Help define how we leverage LLMs across the product surface, from agentic workflows to natural‑language interfaces over our forecasts

Skills

Python

LLMs

ETL

Distributed processing

Customer-facing

AI-native tooling

Tools

FastAPI

Dagster

Dask

GCP

Postgres

BigQuery

Terraform

Docker

Job description

Job Description

At Guac, we’re solving grocery food waste with AI. We forecast exactly how much of each product will sell, helping grocery retailers order and produce the perfect amount of inventory — and we’re building AI-native tools that put those forecasts directly into the hands of store operators and buyers. The grocery industry is enormous (it accounts for 4% of GDP) — and grocery food waste is a huge cost to grocers’ bottom lines, but also to our planet. Today, we’re working with major supermarket chains in the US and Canada, and we’ve scaled to 7-figures in ARR. We’re backed by leading investors including Y Combinator, 1984 Ventures, Collaborative Fund, and angels from Open AI, Instacart, and Citadel Securities. We’ve brought together an exceptional team from Palantir, BCG, Oxford, Cambridge, and MIT to solve intellectually challenging problems and tackle food insecurity and waste with technology.

About the Role

As a Backend Engineer at Guac, you’ll have real impact and ownership over technical decisions, strategy, and product direction.

Your responsibilities will include:

Design and build robust backend services that power mission‑critical ordering and production planning products
Build efficient ETL pipelines to handle billions of rows of data, multiple times per day
Build AI‑powered tools and agents for internal and customer use — exposing our data and forecasting systems via MCP servers, tool‑use APIs, and similar protocols so that LLMs can reason over and act on grocery operations data
Collaborate directly with customers’ technical teams to understand and integrate with their IT infrastructure
Help define how we leverage LLMs across the product surface, from agentic workflows to natural‑language interfaces over our forecasts

About You

3+ years of relevant software engineering experience
Strong proficiency in Python and associated frameworks (FastAPI or similar)
AI‑native: you use Claude Code, Cursor, or similar AI coding tools daily and ship significantly faster because of it
Hands‑on experience building with LLMs — tool use / function calling, RAG, agents, or evals — and familiarity with MCP or similar protocols for connecting models to data and systems
Experience designing and operating data‑intensive backend systems (ETL, large‑scale pipelines, distributed processing)
(Bonus) Experience in customer‑facing technical roles (e.g. forward deployed engineer)
(Bonus) Experience deploying LLM‑powered features to production at scale

What We Offer