Senior Staff Software Engineer, Legal Automation

About the role

This position centers on transforming Coinbase's legal operations through AI. The successful candidate will design and implement a platform of AI agents and automated workflows to replace high-volume, repetitive legal tasks. This includes automating institutional client agreement redlining, supporting SEC filings, managing subsidiary governance, and processing commercial deals. The goal is to build production-grade systems that significantly enhance efficiency and scale within the legal department.

A key responsibility involves owning the institutional client agreement automation system. This entails creating an end-to-end workflow that processes counterparty markups, evaluates them against playbooks, generates redlines with comments, routes for human review, and tracks outcomes. This system will directly impact over 220 institutional clients, requiring robust architecture and a deep understanding of distributed systems fundamentals to ensure reliability and auditability.

Beyond specific use cases, the role requires building a cohesive agent platform with clear governance. This means consolidating existing ad-hoc bots into a standardized, maintainable system with consistent naming, personas, observability, and deployment standards. The engineer will also serve as a technical thought partner to legal leadership, bridging the gap between complex legal processes and engineered solutions, and defining a make-vs-buy strategy for legal tech tools.

The annual base salary for this position ranges from $253,895 to $298,700 USD, with total compensation potentially including equity, bonus eligibility, and benefits.

Skills that matter here

• backend software engineering: This role requires a strong background in backend software engineering to architect and build robust, scalable AI-driven legal infrastructure.
• AI: The position is centered on leveraging AI to automate legal workflows and build an agent platform for legal operations.
• LLM-based applications: Experience with bringing LLM-based applications to production, including evaluation, grounding, and guardrails, is crucial for developing the AI-native legal systems.
• multi-agent orchestration: The role involves designing and operating systems where multiple AI agents collaborate, hand off work, and escalate to humans as needed.
• distributed systems: Understanding distributed systems fundamentals is essential for architecting the agreement automation system, which will handle document processing, routing, and audit trails.
• Exceptional ability to communicate with and learn from non-technical domain experts: Success in this role depends on the ability to translate complex legal workflows into engineered systems and communicate technical constraints to non-technical stakeholders.

Who this role suits

• A person with a strong track record of shipping production systems at scale.
• Someone who thrives in ambiguous, greenfield environments and possesses a relentless drive to achieve ambitious goals.
• An individual with a 'platform mindset' who thinks in terms of primitives, reusability, and standards rather than just point solutions.
• A candidate who can rapidly internalize complex workflows from non-technical experts and translate them into technical designs.

From the employer

What You'll Do:

• Architect and build Legal AI infrastructure — Design and ship a platform of AI agents and automated workflows that replace high-volume, templated legal work including institutional client agreement redlining, SEC filing support, subsidiary governance workflows, and commercial deal processing.
• Own the institutional client agreement automation system — Our highest-priority use case: build an end-to-end agentic workflow that ingests counterparty markups, evaluates them against a structured playbook, generates a first-pass redline with comments, routes for human review, and tracks outcomes. This is a production-grade system affecting 220+ institutional clients in pipeline.
• Build a cohesive agent platform and governance layer — Consolidate a fragmented set of ad-hoc bots and agents into a consistent, documented, maintainable platform with naming conventions, personas, observability, and standards for how Legal agents are built and deployed.
• Act as the technical thought partner to the VP and the broader Legal leadership team — Translate complex legal workflows into engineered systems, and translate engineering constraints back to non-technical stakeholders. The ability to bridge these worlds is as important as the engineering itself.
• Define the make-vs-buy strategy — Evaluate and retire third-party legal tech tools (Harvey, etc.) in favor of purpose-built internal solutions where Coinbase's engineering strength gives us a structural advantage.
• Be the case study — This role is explicitly designed to be a pilot for forward-deployed engineering in non-technical organizations at Coinbase. Success here creates the playbook for how other functions (Finance, HR, Operations) can undergo the same transformation.

Required Skills and Experience:

• 12+ years of backend software engineering experience, with a track record of shipping production systems at scale.
• Proven experience getting LLM-based applications to production — including evaluation frameworks, grounding, guardrails against hallucination, and human-in-the-loop design.
• Multi-agent orchestration experience — you've designed and operated systems where multiple AI agents collaborate, hand off work, and escalate to humans appropriately.
• Exceptional ability to communicate with and learn from non-technical domain experts — you don't need to know legal terminology on day one, but you need to rapidly internalize complex workflows and translate them into engineered systems.
• Platform mindset — you think in primitives, reusability, and standards, not just point solutions.
• Distributed systems fundamentals — the agreement automation system will touch document processing, structured playbook evaluation, routing logic, and audit trails; you need to architect this correctly from day one.
• Relentless drive to set and achieve ambitious goals in ambiguous, greenfield environments.
• Demonstrates the ability to responsibly use generative AI tools and copilots (e.g., LibreChat, Gemini, Glean) in daily workflows, continuously learn as tools evolve, and apply human-in-the-loop practices to deliver business-ready outputs.

Pay Transparency Notice:

• Base salary varies by location (see range below). Total compensation may also include equity and bonus eligibility, and benefits (medical, dental, vision, 401(k)). Annual base salary range (excluding equity and bonus): $253,895—$298,700 USD.
• Application Limit: Candidates may submit a maximum of 3 applications within a 6-month period.
• Equal Opportunity Employer: Coinbase is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, protected veteran status, or genetic information. Applicants with criminal histories will be considered consistent with applicable federal, state, and local laws.
• US Applicants: View [Employee Rights](https://www.dol.gov/sites/dolgov/files/WHD/legacy/files/eppac.pdf), [Know Your Rights](https://www.eeoc.gov/sites/default/files/2023-06/22-088_EEOC_KnowYourRights6.12.pdf), and [E-Verify](https://static-assets.coinbase.com/e-verify.pdf) Notice of Participation.
• Accommodations: If you are an individual with a disability who needs a reasonable accommodation, email us your request and contact info at accommodations[at]coinbase.com. Need screen reading technology? [Click here](https://chromewebstore.google.com/detail/screen-reader/kgejglhpjiefppelpmljglcjbhoiplfn) to download a free compatible screen reader and view the [tutorial](http://www.chromevox.com/tutorial/).
• Data Privacy & Arbitration: By submitting your application, you agree to our [Candidate Privacy Notice](https://www.coinbase.com/legal/applicant_privacy_notice). US applicants: By submitting your application, you agree to [Arbitration of Disputes](https://www.coinbase.com/legal/application-arbitration-agreement).
• AI Disclosure: Coinbase is piloting an AI tool based on machine learning technologies to conduct initial screening interviews to qualified applicants. The tool simulates realistic interview scenarios and engages in dynamic conversation. Coinbase is also piloting an AI interview intelligence platform to transcribe and summarize interview notes, allowing our interviewers to fully focus on you as the candidate. Coinbase will not use AI to make decisions impacting employment.