How many AI roles reference Interpretability right now?

82 active AI roles across 31 companies in our index reference Interpretability as of today. New postings fell 27% in the last 30 days versus the prior 30 (30 → 22).

Which companies are hiring for Interpretability roles?

The companies with the most active Interpretability listings are: Microsoft (9 roles), OpenAI (8 roles), Amazon (7 roles), Meta (7 roles), Anthropic (6 roles).

What AI lifecycle stage does Interpretability belong to?

Interpretability primarily belongs to the evaluation stage of the AI lifecycle. In current hiring, Interpretability roles concentrate at: post-training (51%), agents (17%).

What sectors invest most in Interpretability?

The sectors with the most active Interpretability hiring are: Big Tech, AI Frontier, Banking.

← Tag co-occurrence network

Interpretability

Mechanistic analysis of how neural networks compute — circuit tracing, attribution, behavior decomposition. The research field underpinning safety arguments about model internals.

Primary AI lifecycle stage: evaluation.

As of today, 82 active AI roles across 31 companies in our index reference Interpretability. Hiring concentrates at the post-training (51%) and agents (17%) stages. Most common sectors: Big Tech, AI Frontier, Banking. New postings fell 27% in the last 30 days versus the prior 30 (30 → 22).

Top hiring:

Sector

All Big Tech · 51 AI Frontier · 29 Pharma · 11 Banking · 9 Enterprise · 7 Semiconductors · 6 Data AI · 5 Consumer · 5 Fintech · 4 Telecom · 3 Robotics · 1 Quant · 1 Media · 1 Insurance · 1 Healthcare · 1 Aerospace · 1

Function

All Research · 106 Engineering · 25 Product · 5

Status

All Active only

Sort

AI score Recently posted Company A–Z

FilteredsectorAI Frontier×

29 AI roles tagged interpretability.

Company	Title	Sector	AI score	Other tags
Anthropic	Research Scientist, Interpretability	AI Frontier	10	LLM observability
Anthropic	[Expression of Interest] Research Manager, Interpretability	AI Frontier	10
Anthropic	Anthropic AI Safety Fellow, Canada	AI Frontier	10	Frontier research
Anthropic	Anthropic AI Safety Fellow, UK	AI Frontier	10	Frontier research · Evals · Guardrails · RLHF
Anthropic	Anthropic AI Safety Fellow, US	AI Frontier	10	Frontier research · Evals · Guardrails · RL post-training
OpenAI	Researcher, Interpretability	AI Frontier	10	Frontier research
Anthropic	Research Engineer, Interpretability	AI Frontier	10
Anthropic	Research Manager, Interpretability	AI Frontier	10	LLM observability
Anthropic	Research Scientist, Interpretability	AI Frontier	10
OpenAI	Researcher, Alignment Training	AI Frontier	9	Synthetic data · RL post-training · Evals · Frontier research
OpenAI	Researcher, Alignment Science	AI Frontier	9	RL post-training · Evals · LLM observability · Guardrails
Anthropic	Anthropic Fellows Program — AI Safety	AI Frontier	9	Evals · Guardrails · RL post-training
OpenAI	Researcher, Safety & Privacy	AI Frontier	9	Evals · Guardrails · LLM observability
OpenAI	Threat Modeler, Preparedness	AI Frontier	9	Evals · Guardrails · Agent research
Stability AI	Multimodal Generative AI Researcher	AI Frontier	9	Fine-tuning · Multimodal · Vision · LLM observability · RAG · Agent research · Frontier research · Synthetic data · Model serving · Inference infra
OpenAI	Research Engineer, Privacy	AI Frontier	9	Evals
Lila Sciences	Scientist/Sr. Scientist, AI Safety	AI Frontier	9	Evals · Guardrails · Model serving · Frontier research
Anthropic	Anthropic Fellows Program	AI Frontier	9	Frontier research
Anthropic	Research Engineer, Interpretability	AI Frontier	9	Model serving · Inference infra · Fine-tuning
Anthropic	Privacy Research Engineer, Safeguards	AI Frontier	9	Fine-tuning · RL post-training · Evals
Character AI	Research Engineer, AI Safety & Alignment	AI Frontier	9	Evals · RL post-training · Fine-tuning · Guardrails · LLM observability
OpenAI	Technical Lead, Safety Research	AI Frontier	9	RL post-training · Evals · Guardrails · Frontier research
Anthropic	Research Engineer / Scientist, Model Welfare	AI Frontier	9	Evals
Anthropic	Research Engineer / Scientist, Alignment Science	AI Frontier	9	RL post-training · Evals · Agent research · Guardrails · LLM observability · Frontier research · Agent orchestration · RL robotics
OpenAI	Researcher, Safety Oversight	AI Frontier	9	Evals · Guardrails · RL post-training · Agent research
Anthropic	Research Engineer / Scientist, Safeguards	AI Frontier	9	RL post-training · Agent research · Evals · Guardrails · Agent orchestration · RL robotics
OpenAI	Researcher, Alignment	AI Frontier	9	RL post-training · Evals · Guardrails
Anthropic	Research Scientist, Societal Impacts	AI Frontier	8	Evals · Fine-tuning · Guardrails · LLM observability
xAI	Model Behavior Tutor - Epistemic Rigor & Truthfulness	AI Frontier	8	Evals · Guardrails · Agent research

Frequently asked questions

What is Interpretability in AI?
Mechanistic analysis of how neural networks compute — circuit tracing, attribution, behavior decomposition. The research field underpinning safety arguments about model internals. Primary AI lifecycle stage: evaluation.
How many AI roles reference Interpretability right now?
82 active AI roles across 31 companies in our index reference Interpretability as of today. New postings fell 27% in the last 30 days versus the prior 30 (30 → 22).
Which companies are hiring for Interpretability roles?
The companies with the most active Interpretability listings are: Microsoft (9 roles), OpenAI (8 roles), Amazon (7 roles), Meta (7 roles), Anthropic (6 roles).
What AI lifecycle stage does Interpretability belong to?
Interpretability primarily belongs to the evaluation stage of the AI lifecycle. In current hiring, Interpretability roles concentrate at: post-training (51%), agents (17%).
What sectors invest most in Interpretability?
The sectors with the most active Interpretability hiring are: Big Tech, AI Frontier, Banking.