***This is a hybrid role
About Infinitive
Infinitive is a data and AI consultancy that helps clients modernize, monetize, and operationalize their data to generate lasting value. They pride themselves on their deep industry and technology expertise, ensuring that they drive and sustain the adoption of new capabilities. Infinitive is committed to aligning their team with their clients' culture, ensuring a successful partnership by bringing the right mix of talent and skills for high return on investment.
Infinitive has earned recognition as one of the "Best Small Firms to Work For" by Consulting Magazine, receiving this accolade nine times, most recently in 2026. They have also been honored as a “Top Workplace” by the Washington Post, “Best Places to Work” by the Washington Business Journal, and “Best Places to Work” by Virginia Business.
The Role
The AI Transformation Engineer helps clients rethink how work should be performed when Large Language Models, agents, automation, data, and modern AI development tools are available. The role combines business process understanding, critical thinking, AI engineering, data, and human centered transformation.
The successful candidate can start with an ambiguous challenge and systematically define the required outcome, information, decisions, prompts, context, tools, controls, validation, and human responsibilities needed to deliver it reliably.
What You Will Do:
Business Process Transformation
Lead discovery with executives, business teams, subject matter experts, analysts, and engineers.
Decompose complex processes into steps, decisions, inputs, outputs, rules, dependencies, and exceptions.
Identify bottlenecks, repetitive work, knowledge gaps, and inefficient handoffs.
Challenge legacy process assumptions and design future state workflows around AI enabled capabilities.
Create practical roadmaps that connect prototypes to scalable operating models.
Prompt and Context Engineering
Design system prompts, task prompts, reusable instructions, and multi step prompt workflows.
Translate requirements, policies, and expert knowledge into explicit instructions, constraints, examples, and escalation conditions.
Define structured output formats that people and downstream systems can consume reliably.
Determine what context should be persistent, retrieved dynamically, or supplied by the user.
Optimize model context for quality, speed, cost, and maintainability.
MCP Tools and Handler Engineering
Design MCP servers, clients, and reusable tools where they improve access to enterprise capabilities.
Create clear tool descriptions, efficient parameters, structured responses, and predictable handler behavior.
Connect AI applications with APIs, databases, applications, knowledge repositories, and data platforms.
Plan permissions, authentication, governance, logging, error handling, and recovery.
Define when AI may act, when it should recommend, and when a human must approve.
Markdown and Knowledge Architecture
Create AGENTS.md, CLAUDE.md, README.md, business rules, prompt libraries, process definitions, data dictionaries, tool documentation, architecture notes, and evaluation cases.
Organize large amounts of information so both humans and AI can navigate it efficiently.
Use hierarchy, references, examples, rules, and exceptions to create durable and reusable context.
Manage cross document relationships and reduce unnecessary token consumption.
AI Agents and Workflow Engineering
Design agentic workflows that can plan, retrieve, reason, call tools, and request input.
Define authorization boundaries, memory and state, failure recovery, escalation, and human checkpoints.
Develop reusable components that support multiple use cases.
Use modern AI tools to prototype, document, test, troubleshoot, and accelerate implementation.
AI Evaluation and Quality
Define measurable acceptance criteria and representative evaluation datasets.
Test accuracy, consistency, unsupported claims, latency, token use, and…