Role Summary
What You'll Do
- Own and evolve our agentic data modeling and natural language data retrieval (text-to-sql) capabilities: build and curate semantic models, refine prompts, expand verified question libraries, and measure answer quality so that natural-language analytics get more accurate over time.
- Design and build batch and streaming data pipelines that ingest, transform, and model data from Filevine's product, CRM, billing, and telemetry systems into trusted, well-documented data products.
- Build the data foundations that power agentic AI workflows and LOIS — including feature pipelines, retrieval datasets, and low-latency serving paths for LLM-based reasoning over customer data.
- Establish reliability and governance standards including data quality checks, lineage, monitoring, incident response, access control, and PII handling consistent with our compliance posture.
- Partner with product and engineering stakeholders to define event contracts, model business concepts (matters, firms, users, billing) consistently, and reduce ambiguity across downstream consumers.
- Lead the evaluation and adoption of emerging tools across the modern data stack, recommending right-fit solutions that align with Filevine's strategic and security goals.
- Provide technical mentorship within the Data Engineering team, contribute to code reviews and design documents (DDs/ADRs), and help raise the bar on data engineering practice at Filevine.
- Participate in on-call rotations to maintain SLAs for production data pipelines and analytics surfaces.
What You'll Need
Required
- 5+ years of professional data engineering or backend engineering experience, with a proven track record of delivering production-grade data systems that drive measurable business outcomes.
- Significant hands-on experience operating a modern cloud data warehouse in production (e.g., Snowflake, BigQuery, Redshift, Databricks, Synapse, or equivalent) — including performance tuning, warehouse and cost management, role-based access control, and orchestration of warehouse-native compute (stored procedures, UDFs, streams/tasks, or equivalent).
- Demonstrated experience building with Agentic AI or LLM-powered systems in production — e.g., RAG pipelines, tool-using agents, MCP servers, warehouse-native LLM functions (such as Snowflake Cortex, BigQuery ML, or Databricks AI), or comparable frameworks.
- Expertise in advanced SQL and Python for building reliable, well-tested data pipelines and transformations.
- Experience with modern data modeling and transformation tooling such as dbt, including testing, documentation, and backward-compatible model design that supports self-service analytics.
- Experience with workflow orchestration (Airflow, Dagster, or similar) and cloud-native deployment on AWS, Azure, or GCP.
- Strong fundamentals in data modeling (dimensional, star/snowflake schemas), distributed systems, performance tuning, and data quality / observability principles.
- Professional experience with modern software development methodologies: Agile/Kanban, Git, CI/CD, and DevOps.
- Excellent written and verbal communication skills, with the ability to explain complex technical and data concepts to both technical and non-technical stakeholders.
- B.S., M.S., or Ph.D. in Computer Science, Information Systems, Engineering, or a related field — or equivalent professional experience
Nice to Have
- Hands-on Snowflake experience, including Snowpipe, streams/tasks, data sharing, and cost/governance tuning at scale.
- Experience with Snowflake Cortex Analyst specifically, including authoring and iterating on semantic models and verified queries.
- .NET / C# experience, or familiarity with reading and integrating against a .NET-based application backend.
- Experience using modern UI development tools, particularly Svelte or React
- Experience supporting machine learning workflows: feature stores, training datasets, or real-time scoring infrastructure.
- Experience in SaaS or product-led growth environments, including product analytics and revenue/usage telemetry.
- Infrastructure-as-code experience (Terraform), containerization (Docker, Kubernetes), and deployment (Octopus).
- Familiarity with the legal tech domain, document-heavy data, or working with unstructured data at scale.
- Track record of mentoring engineers and contributing to hiring and team-building.
What You Can Expect
- You will be a core builder of the data and AI foundations that LOIS and Filevine's product surfaces are built on.
- Your work will directly shape how legal professionals query, reason over, and act on their data — and will determine how fast, accurate, and trustworthy our agentic AI experiences become.
Skills Required
- 5+ years of professional data engineering or backend engineering experience
- Significant hands-on experience operating a modern cloud data warehouse in production
- Demonstrated experience building with Agentic AI or LLM-powered systems in production
- Expertise in advanced SQL and Python
- Experience with modern data modeling and transformation tooling such as dbt
- Experience with workflow orchestration tools
- Strong fundamentals in data modeling and distributed systems
- Professional experience with modern software development methodologies
- Excellent written and verbal communication skills
- B.S., M.S., or Ph.D. in Computer Science, Information Systems, Engineering, or a related field
Filevine Compensation & Benefits Highlights
The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Filevine and has not been reviewed or approved by Filevine.
-
Healthcare Strength — Health coverage is described as covering the major bases (medical, dental, vision) and is often framed as decent quality. In some cases, premiums and copays are portrayed as relatively favorable, suggesting tangible value from the plans.
-
Parental & Family Support — Paid parental leave is positioned as a standard, clearly offered benefit. The presence of parental leave alongside disability coverage signals baseline family-support provisions typical of growth-stage tech employers.
-
Fair & Transparent Compensation — Compensation is sometimes framed as fair or reasonable relative to role expectations, with technical roles in particular appearing closer to market-aligned ranges. This creates pockets where pay is perceived as competitive even if not consistently top-of-market across the company.
Filevine Insights
What We Do
Filevine is case management software built for and inspired by real attorneys. As a fully-featured suite of tools, it comes ready to manage every part of a moving case. Assign tasks, upload files or images, monitor staff productivity, and communicate with your client directly from within their case file. Our software is built on the truth that every law firm functions differently. That’s why Filevine is so customizable. Build new case-type templates, design automatic workflows, and receive customized reports on a schedule that fits your needs. Accessing your information is never a problem, because Filevine is hosted on The Cloud. To ensure security, your law firm’s data is protected through state-of-the-art encryption on redundant servers. All you need to get started is an internet connection and your favorite web browser. Learn more at filevine.com.
Gallery
.png){kind=logo}
