The Six Career-Ops Archetypes and Their Key JD Signals

Career-Ops defines six distinct archetypes—AI Platform/LLMOps, Agentic/Automation, Technical AI PM, AI Solutions Architect, AI Forward Deployed, and AI Transformation—each triggered by specific keyword signals in job descriptions to align candidate narratives with role requirements.

The santifer/career-ops repository implements an intelligent classification system that categorizes AI roles into six core career-ops archetypes. This framework, defined in modes/_shared.md, automatically analyzes job descriptions for specific lexical markers to determine role fit and drive downstream application strategies.

Understanding the Six Career-Ops Archetypes

The archetype detection engine in modes/_shared.md scans incoming JDs for distinctive keyword patterns. Each category represents a fundamental AI career trajectory with specific technical and functional markers.

AI Platform / LLMOps

This archetype focuses on infrastructure reliability and large language model operations. Key signals include: "observability", "evals", "pipelines", "monitoring", and "reliability".

Agentic / Automation

Roles in this category emphasize autonomous systems and human-in-the-loop workflows. Detection relies on keywords: "agent", "HITL", "orchestration", "workflow", and "multi-agent".

Technical AI PM

Product-oriented positions that bridge engineering and business strategy. Identifying terms include: "PRD", "roadmap", "discovery", "stakeholder", and "product manager".

AI Solutions Architect

Enterprise-focused design and integration roles. The system flags: "architecture", "enterprise", "integration", "design", and "systems".

AI Forward Deployed

Client-facing implementation and rapid prototyping positions. Signals comprise: "client-facing", "deploy", "prototype", "fast delivery", and "field".

AI Transformation

Change management and organizational adoption specialists. Key indicators are: "change management", "adoption", "enablement", and "transformation".

How Archetype Detection Works in career-ops

The classification logic resides in modes/_shared.md and operates during the JD evaluation flow defined in modes/oferta.md. When processing a posting, the system performs lexical pattern matching against the keyword lists for each archetype.

If the keyword analysis suggests attributes from multiple categories, the system classifies the position as a hybrid role and reports the two closest archetype matches. This dual-tagging captures complex positions that span multiple disciplines, ensuring the candidate narrative addresses both functional areas.

Configuring Your Target Archetypes

Define your target archetypes in modes/_profile.md (never edit the canonical definitions in _shared.md). This configuration specifies which archetypes align with your experience level and career direction:

# modes/_profile.md (excerpt)

archetypes:
  - name: AI Platform / LLMOps
    level: senior
    fit: direct
  - name: Agentic / Automation
    level: staff
    fit: adjacent

Evaluating Job Descriptions Against Archetypes

Run the oferta mode to analyze a specific posting and view the detected archetype classification:

# Evaluate a posting (the mode will print the detected archetype)

node oferta.mjs https://example.com/job/12345

# → Detected archetype: AI Platform / LLMOps

For batch processing pipelines, implement custom filtering logic that leverages the detection system to pre-screen URLs:

// batch/pipeline-filter.mjs
import { readFileSync } from 'fs';
const profile = readFileSync('modes/_profile.md', 'utf8');
const targetArchetypes = ['AI Platform / LLMOps', 'Agentic / Automation'];
// ... after fetching each JD, run the detection logic and keep only those matching targetArchetypes

Impact on Scoring and Pipeline Analytics

The detected archetype influences three critical pipeline functions according to the source code implementation:

• Narrative Alignment: modes/_profile.md uses the archetype to frame your experience narrative toward the role's specific focus area.
• Proof-Point Selection: The system selects relevant achievements from cv.md and article-digest.md based on archetype relevance.
• North-Star Scoring: In modes/triage.md, archetype alignment carries a 30% weight in the quick triage score, directly impacting the North-Star alignment dimension of the overall evaluation.

Additionally, modes/patterns.md aggregates success and failure metrics per archetype across your tracker, enabling data-driven optimization of application strategies for specific role categories.

Summary

• Career-Ops defines six archetypes: AI Platform/LLMOps, Agentic/Automation, Technical AI PM, AI Solutions Architect, AI Forward Deployed, and AI Transformation.
• Detection relies on specific keyword signals defined in modes/_shared.md, with hybrid roles reporting the two closest matches.
• Configure target archetypes in modes/_profile.md with specific seniority levels (e.g., senior, staff) and fit designations (direct or adjacent).
• The archetype drives narrative framing in the profile, proof-point selection from source documents, and contributes 30% weight to the triage scoring algorithm.
• Analytics tracking in modes/patterns.md monitors performance metrics across archetype categories for strategic optimization.

Frequently Asked Questions

How does career-ops determine which archetype applies to a job description?

The system scans the JD text for predefined keyword signals listed in modes/_shared.md. When keywords associated with a specific archetype—such as "observability" for AI Platform/LLMOps or "HITL" for Agentic/Automation—are detected above the threshold frequency, the role is tagged with that classification.

Can a role match more than one career-ops archetype?

Yes. When keyword patterns suggest attributes from multiple categories, the system classifies the position as a hybrid and reports the two closest archetype matches. This captures dual-focus roles such as Technical AI PM positions that also require Solutions Architecture skills.

Where do I configure my preferred archetypes in career-ops?

Define your target archetypes in modes/_profile.md, specifying the archetype name, your experience level, and fit type. Never modify the canonical detection table in modes/_shared.md, as that file contains the global keyword definitions used by the system.

How does archetype detection affect my overall application score?

According to the scoring system implemented in modes/triage.md, archetype alignment contributes 30% of the total weight in the quick triage score. It also influences the North-Star alignment dimension and determines which specific proof points from your cv.md and article-digest.md files are selected for emphasis in the generated application materials.

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}