Program Manager

Prodigy Resources; Denver (CO); Remote; USD 180,000 - 240,000; Full time

Job summary

Prodigy Resources is seeking a senior Technical Program Manager to lead AI delivery initiatives. You will own delivery for multiple engineering pods building agents, RAG pipelines, and integrations with OpenAI, Anthropic, and Google models in a remote US setting.

You will translate vague business asks into scoped milestones, track model accuracy, latency, and cost, and navigate risk and compliance, including HIPAA/PII where needed, while keeping vendor relationships moving.

Qualifications

• 10+ years in technical program or project management, with hands-on engineering.
• Delivery experience with LLM applications and multi-step agent workflows.
• Ability to read architecture diagrams and drive end-to-end delivery across pods.
• Experience with HIPAA/PII risk and compliance when data handling is required.

Responsibilities

• Lead planning across engineering, data, and product to ship AI features.
• Convert vague business asks into scoped milestones with real dates.
• Track model accuracy, latency, and cost next to schedule and budget.
• Own risk and compliance checkpoints, including HIPAA and PII handling when needed.
• Keep cloud/vendor relationships moving with AWS Bedrock, Azure OpenAI, Google Vertex AI.

Skills

LLM delivery

Agent workflows

Clear writing

Agile delivery

Tools

LangChain

LangGraph

MCP (Model Context Protocol)

OpenAI Agents SDK

AWS Bedrock

Azure OpenAI Service

Google Vertex AI

Jira

Job description

This is a senior level Technical Program Manager opportunity for AI delivery. Our client is putting LLM-based products into production and needs a program manager who can read an architecture diagram and still run the room.

About the Role

You'll own delivery for 2 to 4 engineering pods building agents, RAG pipelines, and system integrations on models from OpenAI, Anthropic, and Google. Remote, US-based.

Responsibilities

• Run planning, sequencing, and delivery across engineering, data, and product teams shipping AI features.
• Turn vague asks from business leaders into scoped milestones with real dates.
• Track model accuracy, latency, and cost next to schedule and budget (an agent that works in the demo and costs $9 a call isn't done).
• Own risk and compliance checkpoints, including HIPAA and PII handling when the data calls for it.
• Keep cloud and model vendors moving: AWS Bedrock, Azure OpenAI Service, Google Vertex AI.

Qualifications

• 10+ years in technical program or project management, with some of that time as an engineer or in a hands-on technical role.

Required Skills

• Delivery experience with LLM applications: RAG, prompt and eval design, multi-step agent workflows.
• Working knowledge of agent tooling such as LangChain, LangGraph, Model Context Protocol (MCP), and the OpenAI Agents SDK.
• GenAI work on AWS Bedrock, Azure OpenAI Service, or Google Vertex AI.
• Agile delivery in Jira across several teams at once.
• Clear writing. You'll be explaining model tradeoffs to people who don't care what a token is.

Preferred Skills

• PMP or similar certification.
• Healthcare, finance, or another regulated industry.
• Teams that build with Claude Code or Cursor.