We're seeking an exceptional Senior Data Scientist who can drive both our data warehouse implementation and advanced AI/ML initiatives. This role combines traditional data science with cutting-edge AI development, focusing on delivering actionable insights and automated content generation for legal marketing through sophisticated RAG systems.
Technical Environement
- Data Stack: Fivetran, Snowflake, Metabase
- Data Sources: HubSpot, Vitally, Stripe, Google Analytics, Search Console, PostgreSQL
- AI Infrastructure: Vector databases for embeddings, graph databases, RAG systems
- NLP & Generative AI: Advanced RAG pipelines for content generation
- Integration with phone systems, form submissions, and various marketing platforms
Core Responsibilities
AI Systems Development
- Design and implement sophisticated RAG systems for content generation
- Manage vector databases and embedding systems
- Create and optimize knowledge graphs for enhanced content relationships
- Build and maintain high-quality retrieval pipelines
- Implement evaluation metrics for RAG system performance
- Optimize prompt engineering and context retrieval strategies
Data Architecture
- Work with both relational and non-relational databases
- Design schemas for vector and graph-based data storage
- Implement efficient embedding storage and retrieval systems
- Manage hybrid data systems combining traditional and AI-focused storage
- Ensure data quality across various storage paradigms
Data Warehouse Development
- Lead the implementation and optimization of our data warehouse
- Design and maintain ETL processes using Fivetran
- Ensure data consistency and accuracy across all reporting channels
- Integrate multiple third-party platforms into a unified data model
Analytics & Reporting
- Create comprehensive internal operational analytics
- Design client-facing reports and dashboards
- Develop predictive models for marketing performance
- Generate automated performance insights for various channels
- Implement analytics for RAG system performance
Required Experience
- Strong background in modern AI systems, particularly RAG implementations
- Experience with vector databases and embedding systems
- Knowledge of graph databases and their applications
- Expert-level SQL and data modeling skills
- Experience with Fivetran, Snowflake, and Metabase (or similar tools)
- Background in NLP and generative AI
- Understanding of both relational and non-relational database paradigms
- Strong understanding of marketing analytics and SEO metrics
What Sets You Apart
- Experience building production-grade RAG systems
- Background in optimizing embedding models and vector search
- Knowledge of graph-based AI applications
- Experience with legal or marketing tech domains
- Track record of building reliable data pipelines
- Ability to balance speed with quality
- Strong communication skills for working with non-technical stakeholders
Technical Skills
- Vector databases (e.g., Pinecone, Weaviate, or similar)
- Graph databases (e.g., Neo4j, Amazon Neptune)
- Traditional SQL databases
- Embedding models and vector operations
- RAG system design and implementation
- Knowledge graph development
- Modern NLP and LLM frameworks
- Data warehouse technologies
Ideal Candidate Profile
You're perfect for this role if you:
- Have hands-on experience building and optimizing RAG systems
- Understand the nuances of different data storage paradigms
- Can effectively work with embeddings and vector operations
- Execute quickly and independently without sacrificing quality
- Thrive in ambiguous, fast-paced environments
- Can translate business needs into technical solutions
- Focus on delivering practical solutions over theoretical perfection
What Makes This Role Unique
This position offers the opportunity to:
- Build and optimize state-of-the-art RAG systems
- Work with diverse data paradigms (relational, vector, graph)
- Shape the future of AI-driven content creation
- Own the entire data stack from warehouse to AI implementation
- Work independently while collaborating with product and engineering teams
This is an ideal role for a senior data scientist looking to work with cutting-edge AI technology while having the freedom to implement and optimize sophisticated data systems in a high-growth environment.
Note: This is a key individual contributor role - we're looking for someone who can execute independently rather than manage a team.
About Us
FirmPilot AI is at the forefront of revolutionizing legal marketing, dedicated to empowering law firms with cutting-edge artificial intelligence solutions. We're on a mission to transform the legal landscape by developing AI tools that enhance efficiency, accuracy, and decision-making in legal marketing.
At FirmPilot AI, we're not just building software; we're crafting the future of legal marketing. Our team pushes the boundaries of AI capabilities, always with a keen focus on the unique needs and ethical considerations of the legal profession. We believe that AI, when developed responsibly, can dramatically improve access to justice and legal services worldwide.
We're an equal opportunity employer, valuing diversity in all its forms. We don't just accept differences - we celebrate them, support them, and thrive on them for the benefit of our employees, our products, and our community.
Join FirmPilot AI and be part of a team that's not just witnessing the AI revolution in law - we're leading it. Help us shape a future where legal professionals are empowered by AI to serve justice more effectively and efficiently than ever before.
