Lead AI Engineer Job Denver area,Colorado USA,IT/Tech

Requirements

5+ years of software or ML engineering experience, with 2+ years of building LLM systems in production
(Desirable) Expert-level proficiency in Python, plus Type Script or Go for full-stack AI applications
(Desirable) Proven ability to communicate complex AI concepts clearly to non-technical stakeholders—translating engineering trade-offs and model behavior into business terms that inform decisions
(Desirable) Experience implementing production RAG systems using Snowflake Cortex Search, pgvector, hybrid search, and re‑ranking strategies
(Desirable) Hands‑on experience building MCP (Model Context Protocol) servers and clients
Proven track record implementing AI observability
(Desirable) Experience working with LLM APIs (OpenAI, Anthropic, Azure, Gemini) and cloud platforms (AWS Sage Maker, Lambda, S3, Bedrock)
(Desirable) Familiarity with CI/CD and MLOps tooling (MLflow, Weights & Biases, Snowflake ML Registry)
(Desirable) Demonstrated application of responsible AI practices on live deployments, including bias checks, output validation, and human‑in‑loop escalation
(Desirable) A track record of proactively evaluating and introducing new AI tools or frameworks that deliver tangible improvement—not just awareness of trends but applied adoption
(Desirable) Experience managing production incidents and model rollbacks in high‑stakes environments
Snowpark or external functions in Snowflake
(Desirable) Experience with enterprise SaaS platforms (Service Now, Salesforce, or similar)
Workflow orchestration tools (Airflow, n8n, or similar)
(Desirable) Authentication and access control concepts (OAuth, RBAC, SSO)
(Desirable) Exposure to vector search or semantic retrieval technologies

What the job involves

As a part of a new team focused on accelerating AI adoption and usage, the AI Engineer will design and deploy AI‑powered automation, and intelligent agents embedded directly into business operations. This role operationalizes generative AI using governed enterprise data, leveraging enterprise data as the data foundation, and enterprise tools for orchestration and execution
The position partners with Data, IT, and business teams to automate workflows, support decision‑making, and improve operational efficiency. The focus is on applying AI to real processes—not research or model training. This role will report up into the VP of AI, Collaboration and Data's team
Build internal AI assistants and copilots for support, operations, and business teams
Implement Retrieval Augmented Generation (RAG) using Snowflake data and curated metrics
Ground AI responses using modeled enterprise data rather than documents alone
Implement prompt strategies, guardrails, and response evaluation techniques
Automate operational processes such as ticket triage, routing, approvals, and document handling
Develop AI‑driven classification, summarization, and recommendation services
Implement human‑in‑the‑loop workflows and exception handling
Continuously improve workflows based on business outcomes and user feedback
Build and maintain AI‑powered backend services, APIs, and microservices
Integrate AI capabilities with enterprise systems (ITSM, CRM, ERP, and internal applications)
Troubleshoot failures across data pipelines, orchestration, and model inference layers
Participate in technical design and architecture discussions
Utilize Snowflake as the trusted data source for AI decisions
Use dbt models as the semantic and business logic context for automation
Enable real‑time and batch data‑driven decision support
Ensure AI actions align with defined business metrics and data definitions
Implement serverless workflows using AWS (Lambda, Step Functions, API Gateway, S3, Event Bridge)
Monitor system performance, latency, and operational reliability
Track AI usage, accuracy, and cost efficiency
Implement logging, auditing, and traceability of AI decisions

#J-18808-Ljbffr