Agentic AI Engineer - In Person, Park City

About SubcontractorHub - Headquartered in Park City, Utah

We are bringing order to the chaos of the home services industry. SubcontractorHub is a comprehensive, AI-powered operating system tailored 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.

The Role

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

In this role, you'll develop intelligent agents that can reason, plan, retrieve information, use tools, and safely execute complex tasks within a multi-tenant SaaS environment. You'll help shape our long-term AI strategy by designing robust agent architectures, building rigorous evaluation frameworks, and implementing the safeguards required for production AI systems.

We believe the best products are built through close collaboration. This is a full-time, in-person role where you'll work alongside our leadership, product, and engineering teams to shape the future of AI in one of the largest underserved industries.

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 using PyTorch and Hugging Face (leveraging LoRA and PEFT techniques where appropriate).
• Design Rigorous Evaluations: Build the evaluation harness alongside the feature. Handle dataset curation, define metrics, utilize LLM-as-judge approaches, and analyze agent trajectories.
• Ensure Production Safety: Implement strict 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 & Communication: Raise the engineering bar by writing clear, precise PR descriptions, technical proposals, and architecture notes that a distributed team can rely on.

Tech Stack

• Backend API: Python, FastAPI, Pydantic, SQLModel
• AI & Agents: LangGraph, LangChain, Pydantic AI
• ML & Model Dev: PyTorch, Hugging Face, scikit-learn, XGBoost, NeuralProphet
• Data Processing: Polars, Pandas, Databricks
• PDF & Browser Automation: PyPDF, PyPDFium2, PyMuPDF, Playwright
• Databases & Cache: PostgreSQL, MariaDB, Valkey
• Observability: Logfire, Sentry, Datadog

What We Are Looking For

• Proven Production Experience: 5+ years of hands-on applied AI/ML experience. 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 specific failure modes that only appear at scale.
• Applied Fine-Tuning Discipline: You possess the practical knowledge to curate datasets and design evaluations, coupled with the discipline to know exactly when fine-tuning is necessary versus when prompting or RAG is the right tool.
• Data Fluency: You are 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 or higher degree 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 experience developing AI applications for B2B SaaS, business management platforms, or the construction/contractor industry.