AI App Lead

Confiz•Denver, CO

About The Position

Confiz is seeking an AI App Lead in Denver, CO, to own the architecture and hands-on delivery of AI-powered applications built with Databricks, Python, and React. The role sets technical direction for data, machine learning, and full-stack engineers while contributing production code. It involves designing LLM, RAG, and agentic systems on the Databricks Lakehouse, exposing them through Python services, and delivering them through React interfaces. The lead is accountable for secure, scalable, cost-efficient production solutions and for ensuring that delivered code matches the architecture. The role partners with product owners and stakeholders to translate business requirements into technical architecture and communicate trade-offs to technical and non-technical audiences. Confiz describes its global team as working on innovative enterprise projects and products for Fortune 100 retail and CPG companies, leading store chains, fast-growth fintech companies, and Silicon Valley startups. The company highlights its processes and culture, ISO certifications, collaborative learning, and use of cutting-edge technologies.

Requirements

10+ years of software engineering experience, including 3+ years designing and delivering production AI/ML systems and hands-on generative AI work.
Demonstrated experience leading engineers and setting technical direction while remaining hands-on in code.
Advanced Python skills, including production services, asynchronous programming, testing, packaging, and PySpark.
Hands-on Databricks Lakehouse experience with Delta Lake, Unity Catalog, MLflow, Databricks Workflows, and Spark-based processing; experience with Model Serving and Vector Search.
Strong React and TypeScript skills, including component architecture, state management, API integration, and streaming or real-time user interfaces.
Deep understanding of LLMs, RAG architectures, agentic systems, prompt engineering, LLM evaluation, and model fine-tuning.
Proven experience designing scalable distributed systems, REST APIs, and microservices, with a solid grasp of system design and security principles.
Strong SQL, data modeling, ETL/ELT pipeline design, and data governance skills.
Experience with AI and data services on Azure, AWS, or GCP.
Hands-on infrastructure-as-code experience with Terraform, Bicep, or CloudFormation, including Databricks Asset Bundles (DABs) for versioning and deploying jobs, pipelines, and model-serving endpoints through CI/CD.
Proficiency in CI/CD, Git, automated testing, and the full software development life cycle.
Strong stakeholder communication skills, including translating architecture into business value for technical and non-technical audiences.

Nice To Haves

Databricks certifications, such as Generative AI Engineer Associate, Machine Learning Professional, or Data Engineer Professional.
Experience with agent and orchestration frameworks such as LangGraph, LangChain, LlamaIndex, or DSPy, and the Model Context Protocol (MCP).
Experience with vector databases beyond Databricks Vector Search, such as Pinecone, Weaviate, or pgvector.
Exposure to Docker and Kubernetes.
Experience with Next.js, design systems, and accessible UI development.
Prior experience in a client-facing, pre-sales, or solutioning capacity.
Experience in a regulated industry such as financial services.

Responsibilities

Lead end-to-end architecture of AI solutions, including LLM applications, RAG pipelines, and agentic workflows, from data ingestion through the user interface.
Design and build data and ML pipelines on Databricks using Delta Lake, Unity Catalog, MLflow, Databricks Workflows, and Mosaic AI capabilities.
Build and review production Python services, such as FastAPI services, that expose models, retrieval, and agents through secure, well-documented REST APIs.
Architect and contribute to React (TypeScript) front ends for AI experiences, including chat interfaces, streaming responses, source citations, and human-in-the-loop review screens.
Select LLM providers, models, and retrieval options based on quality, latency, cost, and data-governance fit.
Establish LLMOps and MLOps practices, including model and prompt versioning, automated evaluation, tracing, monitoring, drift detection, and retraining.
Produce architecture and design artifacts for complex AI applications and ensure delivered code meets those designs.
Lead code and architecture reviews and mentor engineers on RAG, agent design, prompt engineering, and evaluation.
Ensure solutions meet security, privacy, and compliance standards, including access controls, PII handling, guardrails, audit trails, and responsible AI practices.
Identify and automate fixes for recurring issues to improve the operational stability and cost efficiency of AI workloads.
Translate business requirements into technical architecture with product owners and stakeholders, communicating trade-offs to technical and non-technical audiences.