ai tools engineer

Qualifications

• Strong Python + JavaScript/TypeScript experience
• Experience building internal tools or dashboards (Streamlit, , custom UI, etc.)
• Knowledge of how LLMs work (tokens, structure, embeddings, inference)
• Ability to design clean interfaces for engineering teams
• Strong debugging and organizational mindset
• Experience working in fast-moving environments
• Familiarity with vector DBs, embedding search, or RAG
• Experience instrumenting LLM behavior or building evaluation metrics
• ML experience (not required but helpful)
• Unity/Unreal experience on the tooling side
• DevOps knowledge for local model serving setups
• Consistent behavior across hundreds of characters
• Ability to design the foundational AI infrastructure
• Freedom to invent new evaluation and debugging methods
• Real impact on the direction of a multi-world, multi-game AI ecosystem
• AI Lead Engineer – Model behavior requirements & evaluation needs
• LLM Engineers – Integration of testing tools and routing systems
• Prompt/Dialogue Engineers – Tone evaluation tools, output consistency tests
• Any AI-related tooling you've created

Benefits

• Clearer debugging
• Safer deployments
• This role gives you massive visibility — everything the AI team builds flows through your tools
• Phantom equity (early team access)
• Ownership over the entire tooling pipeline

Responsibilities

• Memory debugging systems
• "I love building dashboards, inspectors, and developer utilities."
• "I want to make AI behavior predictable and measurable."
• You will create the internal tools that make LLM development faster, more reliable, and more measurable
• Cross-game NPC behavior tracking
• This is a high-leverage engineering role — you amplify the productivity of the entire AI division
• Build dashboards for evaluating LLM output quality, emotion, consistency, and safety
• Develop tools for testing prompts, memory injections, and personality variations
• Create internal utilities for comparing models, tokens, outputs, and structural patterns
• Implement logging + monitoring systems for AI behavior
• Support rapid iteration of AI systems with automation utilities
• Build "debugging lenses" for memory, emotion, and persona routing
• Work closely with AI engineers to integrate tools into workflows
• Maintain internal documentation + developer instructions
• This role sits at the intersection of AI, engineering, and developer productivity
• Your work is the infrastructure layer for every AI-driven character in the ecosystem
• Memory/Emotional Engine Engineer – State debugging layers
• CTO – Infrastructure + model serving
• Tokenization Patterns & Debugging

Full Description

Location:

Remote

Compensation:

Early-team phantom equity pool

Type:

Full-Time or Contractor

About the Opportunity

Inkognido is building the AI backbone of a new entertainment ecosystem — avatar intelligence, emotional engines, and dynamic NPC systems that evolve across multiple games and worlds.

To make this possible, we need elite-level internal tools:

Evaluation dashboards

Prompt-testing utilities

Behavior-routing tools

Model comparison suites

Emotional output analyzers

Memory debugging systems

The AI Tools Engineer builds the systems our entire AI team relies on.

If you've ever said:

"The model isn't the hard part — the tooling is."

"I love building dashboards, inspectors, and developer utilities."

"I want to make AI behavior predictable and measurable."

"Give me a chaotic ML pipeline and I'll bring order to it."

Then this role is EXACTLY for you.

What You'll Build

You will create the internal tools that make LLM development faster, more reliable, and more measurable.

Your work directly powers:

VEL (our avatar intelligence system)

NPC emotional engines

Personality tuning

Dialogue evaluation

Memory consistency

Cross-game NPC behavior tracking

This is a high-leverage engineering role — you amplify the productivity of the entire AI division.

Responsibilities

Build dashboards for evaluating LLM output quality, emotion, consistency, and safety

Develop tools for testing prompts, memory injections, and personality variations

Create internal utilities for comparing models, tokens, outputs, and structural patterns

Implement logging + monitoring systems for AI behavior

Support rapid iteration of AI systems with automation utilities

Build "debugging lenses" for memory, emotion, and persona routing

Work closely with AI engineers to integrate tools into workflows

Maintain internal documentation + developer instructions

Requirements

Must Have:

Strong Python + JavaScript/TypeScript experience

Experience building internal tools or dashboards (Streamlit, , custom UI, etc.)

Knowledge of how LLMs work (tokens, structure, embeddings, inference)

Ability to design clean interfaces for engineering teams

Strong debugging and organizational mindset

Experience working in fast-moving environments

Nice to Have:

Familiarity with vector DBs, embedding search, or RAG

Experience instrumenting LLM behavior or building evaluation metrics

ML experience (not required but helpful)

Unity/Unreal experience on the tooling side

DevOps knowledge for local model serving setups

This role sits at the intersection of AI, engineering, and developer productivity.

Why This Role Matters

Because next-gen AI development doesn't scale without great tools.

You are the force multiplier.

You enable:

Faster iteration

Clearer debugging

Safer deployments

Higher-quality personality systems

Consistent behavior across hundreds of characters

Your work is the infrastructure layer for every AI-driven character in the ecosystem.

This role gives you massive visibility — everything the AI team builds flows through your tools.

What You Get

Phantom equity (early team access)

Ownership over the entire tooling pipeline

Ability to design the foundational AI infrastructure

Freedom to invent new evaluation and debugging methods

Direct collaboration with Founders + Head of AI

Real impact on the direction of a multi-world, multi-game AI ecosystem

How This Role Works With Others

You will work most closely with:

AI Lead Engineer – Model behavior requirements & evaluation needs

LLM Engineers – Integration of testing tools and routing systems

Prompt/Dialogue Engineers – Tone evaluation tools, output consistency tests

Memory/Emotional Engine Engineer – State debugging layers

CTO – Infrastructure + model serving

Realms Team – NPC integration testing utilities

Deck Team – Tools for avatar personality previews

Your work supports nearly EVERY system.

Study Links (Internal Use)

(Not visible to applicants unless you want it to be.)

LLM Evaluation Frameworks

Model Comparison Methodologies

Tokenization Patterns & Debugging

Output Quality Metrics

Memory Injection Techniques

Emotional Modeling Systems

How to Apply

Use our application hub:

Or email:

[email protected]

[email protected]

[email protected]

[email protected]

Include:

Resume / LinkedIn

GitHub or tools portfolio

Any AI-related tooling you've created

A short note on why tooling is your passion