Agentic AI Engineer

SubcontractorHub; Park City, Northern (UT, KY); Hybrid; USD 140,000 - 180,000; Full time

Job summary

SubcontractorHub, an AI-powered OS for contractors in solar, roofing, and HVAC, seeks an Agentic AI Engineer to design, build, and deploy production-grade AI systems powering critical workflows.

You will own the full lifecycle from architecture through deployment, evaluation, and continuous improvement in a full-time, in-person role based in Lehi or Park City, Utah.

Qualifications

• 5+ years of production AI/ML experience.
• Prompt design, tool use, retrieval-augmented generation (RAG).
• Experience with dataset curation and evaluation design.
• SQL against large relational databases and data pipelines.
• Strong CS foundations in software development and neural networks.
• Master's degree or higher in CS/AI or equivalent practical experience.

Responsibilities

• End-to-end ownership from problem framing to post-launch monitoring.
• Build agentic workflows with LangGraph and Python.
• Train, fine-tune, and evaluate models with PyTorch and Hugging Face.
• Design evaluation harness: datasets, metrics, LLM-as-judge, agent trajectories.
• Implement production safety guardrails for a multi-tenant SaaS environment.
• Provide technical leadership with clear PRs, architecture notes, and proposals.

Skills

Applied AI/ML

Agentic design

Data pipelines

SQL proficiency

Software fundamentals

Education

Master's degree or higher in CS/AI

Tools

LangGraph

LangChain

Pydantic AI

PyTorch

Hugging Face

scikit-learn

XGBoost

NeuralProphet

Polars

Pandas

Databricks

PyPDF

Playwright

PostgreSQL

MariaDB

Valkey

Logfire

Sentry

Datadog

Job description

We are bringing order to the chaos of the home services industry. SubcontractorHub is a comprehensive, AI-powered operating system built for contractors in solar, roofing, and HVAC. Every day, thousands of contractors lose hours to paperwork, manual processes, disconnected software, and administrative overhead. We're changing that.

Our platform combines CRM, project management, contracts, finance, and operations into a single system powered by intelligent AI agents that actually get work done.

As an Agentic AI Engineer, you will design, build, and deploy production-grade AI systems that power critical workflows across the platform. Working closely with our AI research team, you'll turn cutting-edge research into reliable, scalable features contractors use every day — owning the full lifecycle from architecture and prototyping through deployment, evaluation, monitoring, and continuous improvement.

You'll develop intelligent agents that can reason, plan, retrieve information, use tools, and safely execute complex tasks inside a multi-tenant SaaS environment, and help shape our long-term AI strategy through robust agent architectures, rigorous evaluation frameworks, and the safeguards production AI requires.

We believe the best products are built through close collaboration. This is a full-time, in-person role based in either our Lehi or Park City, Utah office, working alongside our leadership, product, and engineering teams.

What you'll do

• End-to-end ownership: take AI features from problem framing and research prototypes through productization and post-launch monitoring.
• Build agentic workflows: develop and orchestrate advanced multi-agent systems and LLM-based applications using LangGraph and Python.
• Model development: train, fine-tune, and evaluate models with PyTorch and Hugging Face, applying LoRA and PEFT techniques where appropriate.
• Design rigorous evaluations: build the evaluation harness alongside the feature — dataset curation, metric definition, LLM-as-judge approaches, and agent-trajectory analysis.
• Ensure production safety: implement operational guardrails for a multi-tenant SaaS environment, including prompt-injection defenses, PII handling, output validation, jailbreak prevention, and circuit breakers for agent loops.
• Technical leadership and communication: raise the engineering bar with clear, precise PR descriptions, technical proposals, and architecture notes a distributed team can rely on.

Tech stack

• Backend API: Python, FastAPI, Pydantic, SQLModel
• AI and agents: LangGraph, LangChain, Pydantic AI
• ML and model development: PyTorch, Hugging Face, scikit-learn, XGBoost, NeuralProphet
• Data processing: Polars, Pandas, Databricks
• PDF and browser automation: PyPDF, PyPDFium2, PyMuPDF, Playwright
• Databases and cache: PostgreSQL, MariaDB, Valkey
• Observability: Logfire, Sentry, Datadog

What we're looking for

• Proven production experience: 5+ years of hands-on applied AI/ML work. You have shipped systems with real users behind them, not just research papers or personal projects.
• Agentic expertise: deep familiarity with prompt design, tool use, retrieval-augmented generation (RAG), memory architectures, and the failure modes that only appear at scale.
• Applied fine-tuning discipline: the practical knowledge to curate datasets and design evaluations, plus the discipline to know when fine-tuning is necessary versus when prompting or RAG is the right tool.
• Data fluency: comfortable writing SQL against large relational databases, building data pipelines, and extracting clear training signals from messy production data.
• Strong CS foundation: advanced proficiency in software development, pattern recognition, and neural networks.
• Education: master's degree or higher in computer science, AI, or a related field — or equivalent practical experience.

Bonus points

• Computer vision: experience with image segmentation, object detection, or polygon extraction is a strong advantage.
• Domain experience: previous work building AI applications for B2B SaaS, business management platforms, or the construction and contracting industry.