AI/ML Engineer

Sledge; United States; Remote; USD 150,000 - 210,000; Full time

Benefits offered by this job

Fully remote

Flexible hours

Direct access to founding team

Weekly deployment cadence

Job summary

Sledge is hiring an ML/AI Engineer to build and run the AI systems that power Sledge Construction AI. You will work on a production multi-agent system, written in Python and FastAPI, with Pinecone for vector storage, and an internal agent fleet.

This is a build role, focused on production reliability and weekly deployments. You will design and refine agents, write prompts, and implement evaluation loops to maintain quality, while collaborating with the engineering and QA teams to ship features

Qualifications

• Hands-on production experience building with LLMs.
• Strong Python skills and backend experience (FastAPI).
• Experience building RAG pipelines with vector databases.
• Experience training or fine-tuning models, not just prompting.
• Background with multi-agent systems and agent orchestration.
• Experience deploying AI features on weekly cadences.

Responsibilities

• Build, extend, and maintain Sledge's multi-agent AI system in Python and FastAPI.
• Design and improve retrieval and vector search using Pinecone.
• Build and refine agents in Sledge's internal fleet and design new ones.
• Write and tune prompts and create evaluation loops for regression.
• Fine-tune or train models when prompting and RAG aren't enough.
• Collaborate with engineering to ship AI features on a weekly cadence.
• Work with QA to ensure proper testing, including Playwright-based tests.
• Debug and improve agents in production, not just in notebooks.

Skills

Python

LLMs

RAG pipelines

Vector databases

Multi-agent systems

Model fine-tuning

FastAPI

Production deployment

Tools

Pinecone

Pandas/Numpy

Playwright

Job description

About Sledge

From bid to build to paid. From the office to the field to the entire company. Sledge is Construction AI.Sledge is the agentic, AI-native operating system for construction, handling the busywork of running a construction business so builders can spend more time building and less time on paperwork. Built for subcontractors and small to mid-size general contractors, Sledge is already live with a growing group of beta users. The AI isn't a feature bolted onto Sledge, it's the core of the product.

About the role

Sledge is hiring an ML/AI Engineer to build and run the AI systems that make Sledge Construction AI, not just construction software with a chatbot bolted on. Sledge already runs a multi-agent AI system in Python and FastAPI, with Pinecone for vector storage, and an internal agent fleet that includes agents like Forge, Mimir, Anvil, Mason, Beacon, Scout, Warden, Crane, and Vault. This role reports to Sledge's engineering team and works hands-on inside that system, not around it.This is a build role, not a research role. Sledge needs agents that work reliably in production, on a weekly deployment cadence, not a paper or a demo.

What you'll do

Build, extend, and maintain Sledge's multi-agent AI system, built in Python and FastAPIDesign and improve retrieval and vector search using PineconeBuild and refine the agents in Sledge's internal fleet, and design new ones as Sledge needs themWrite and tune prompts, and build the evaluation loops that catch when an agent gets worse, not just betterFine-tune or train models when prompting and RAG aren't enough to get the job doneWork with the rest of engineering to ship AI features on Sledge's weekly deployment cadenceWork with QA to get AI features properly tested, including through Sledge's Playwright-based testing toolDebug and improve agents in production, not just in a notebook

What we're looking for

Must-havesRequired: hands-on production experience building with LLMs, not just personal projects or courseworkRequired: strong Python skills, comfortable in a FastAPI-style backendRequired: hands-on experience building RAG pipelines, from chunking and embeddings through retrieval and rerankingRequired: experience training or fine-tuning models, not just prompting a hosted APIReal experience with vector databases beyond knowing the term: indexing strategies, embedding models, and retrieval quality, ideally including PineconeExperience building or working with multi-agent systems, including agent-to-agent orchestration and handoffs, not just a single agent calling toolsComfortable owning an AI feature from prototype to production, not just the model itselfComfortable moving at startup speed, shipping weeklyNice-to-havesExperience with agent orchestration approaches or frameworks, and a clear opinion on when to use one versus build customFamiliarity with LLM evaluation techniques: evals, hallucination detection, and prompt regression testingA habit of following LLM and agent research and turning it into something that ships, not just reading itExperience with TypeScript, Next.js, or ExpressExperience with Supabase, PostgreSQL, or Drizzle ORMExperience with AWSInterest or experience in construction, trades, or B2B software

Perks and benefits

Fully remote, work from anywhere in the worldFlexible hours, work when you're most productiveDirect access to the founding team and engineering, no layers of managementYou're building the actual AI core of the product, not a wrapper around someone else's modelShip weekly, see your work in production fast

Equal opportunity

Sledge is an equal opportunity employer. Sledge welcomes applicants of every background and does not discriminate on the basis of race, color, religion, sex, national origin, age, disability, or any other protected status.