Agentic AI Engineer

Role: Agentic AI Engineer

Location: Austin, TX/Dallas, TX

Type: Contract

JD

:- agentic data engineerin

g- Good understanding of FinOps and tooling, and is an expert in distributed system

sResponsibilities

:· Understand the data needs of stakeholder teams in terms of key data models and reporting, and translate that into technical requirement

s· Define, build and manage key data pipelines in dbt that transform raw logs into canonical dataset

s· Establish high data integrity standards and SLAs to ensure timely, accurate delivery of dat

a· Develop insightful and reliable dashboards to track performance of core metrics that will deliver insights to the whole compan

y· Build foundational data products, dashboards and tools to enable self-serve analytics to scale across the compan

y· Influence the future roadmap of Product and GTM teams from a data systems perspectiv

e· Become an expert in our organization’s data models and the company's data architectur

eYou might be a good fit if you have

:· 5+ years of experience as an Analytics Data Engineer or similar Data Science & Analytics roles, preferably partnering with GTM and Product leads to build and report on key company-wide metrics

.· A passion for the company's mission of building helpful, honest, and harmless AI

.· Expertise in building multi-step ETL jobs, building robust data models through tooling like dbt; proficiency with workflow management platforms like Airflow and version control management tools through GitHub

.· Expertise in SQL and Python to transform data into accurate, clean data models

.· Experience building data reporting and dashboarding in visualization tools like Hex to serve multiple cross-functional teams

.· A bias for action and urgency, not letting perfect be the enemy of the effective

.· A “full-stack mindset”, not hesitating to do what it takes to solve a problem end-to-end, even if it requires going outside the original job description

.· Experience building an Analytics Data Engineering (or similar) function at start-ups

.· A strong disposition to thrive in ambiguity, taking initiative to create clarity and forward progress

.
2

) Key Responsibiliti

es · Prompt Engineering Excellence : Design, test, and optimize system prompts and feature-specific prompts that shape Claude’s behavior across consumer and API product

s. · Evaluation Development : Build and maintain comprehensive evaluation suites that ensure model quality and consistency across product launches and update

s. · Cross-functional Collaboration : Partner closely with product teams, research teams, and safeguards to ensure new features meet quality and safety standard

s. · Model Launch Support : Play a critical role in model releases, ensuring smooth rollouts and catching regressions before they impact user

s. · Infrastructure Contribution : Help build and improve the frameworks and tools that allow teams to develop and test prompts and features with confidenc

e. · Knowledge Transfer : Mentor product engineers on prompt engineering best practices and help teams build their first evaluation

s. · Rapid Iteration : Work in a fast-paced environment where model capabilities advance daily, requiring quick adaptation and creative problem-solvin

g.Required Qualificatio

ns· 5+ years of software engineering experience with Python or similar language

s.· Demonstrated experience with LLMs and prompt engineering (through work, research, or significant personal projects

).· Strong understanding of evaluation methodologies and metrics for AI system

s.· Excellent written and verbal communication skills – you’ll need to explain complex model behaviors to diverse stakeholder

s.· Ability to manage multiple concurrent projects and prioritize effectivel

y.· Experience with version control, CI/CD, and modern software development practice

s.Preferred Qualificatio

ns· Experience with Claude or other frontier AI models in production setting

s.· Background in machine learning, NLP, or related field

s.· Experience with A/B testing and experimentation frameworks (e.g., Statsig

).· Familiarity with AI safety and alignment consideration

s.· Experience building tools and infrastructure for ML/AI workflow

s.· Track record of improving AI system performance through systematic evaluation and iteratio