Machine Learning Engineer, CX Intelligence

div class= content-intro p Ready to do the most impactful work of your career? At a href= https://www.coinbase.com/?utm_campaign=mt_o_m_w_m_m__coi_0_jd-onchain utm_source=coinbase Coinbase /a , we are uncompromising on our mission to increase economic freedom. The bar is high, the environment is intense, and we like it that way. This isn't a place for complacency, it’s a place to be pushed past your perceived limits. If you're ready to build the future of finance alongside people who refuse to settle for good enough, you belong here. Coinbase is a remote-first, but not remote-only company. Expect to get together quarterly for intense in-person working sessions called “surges.” a href= https://www.coinbase.com/careers learn more about working at Coinbase /a . /p /div p class= mb-2 whitespace-pre-wrap The CX Intelligence Engineering team, part of Coinbase's Enterprise Applications and Architecture org, builds the multi-agent platform powering Coinbase Chat, Help Center, and agent tooling. As a Machine Learning Engineer on this team, you'll design and scale the agentic systems that automate complex customer support workflows, connecting LLMs with internal APIs and tools to deliver fast, accurate, and compliant AI-powered experiences for millions of customers. /p

p class= mb-2 whitespace-pre-wrap strong What you'll do: /strong /p

ul

li Architect multi-agent systems using advanced orchestration frameworks (LangGraph, Google ADK) to automate complex customer support procedures end-to-end. /li

li Build and scale integrations using Model Context Protocol (MCP) to connect LLMs with internal Coinbase APIs, databases, and third-party tooling. /li

li Develop automated LLM-as-a-judge evaluation pipelines to monitor, measure, and improve the performance of non-deterministic AI agents in production. /li

li Implement RAG, fine-tuning, and prompt engineering techniques to ensure chatbot responses are grounded, accurate, and compliant with Coinbase policies. /li

li Ship production-ready Python services that are resilient, low-latency, and capable of handling Coinbase-scale traffic across asynchronous microservices. /li

li Partner with Conversation Design and Product to translate complex business logic into executable agent procedures within the decentralized architecture. /li

/ul

p class= mb-2 whitespace-pre-wrap strong Required Skills and Experience: /strong /p

ul

li 3+ years building and scaling ML/AI systems in production, with demonstrated experience implementing agentic Loop or ReAct based systems where AI takes actions autonomously. /li

li Deep understanding of the LLM lifecycle including context window management, token optimization, structured output parsing (Pydantic, JSON mode), and multi-agent orchestration frameworks (LangGraph, Google ADK, or similar). /li

li Strong proficiency in Python with hands-on experience in microservices architecture, asynchronous programming, high-throughput APIs, and vector databases (Pinecone, Weaviate, or equivalent). /li

li Demonstrated ability to explain model behaviors and technical trade-offs to non-technical stakeholders across CX, Legal, and Product teams. /li

li Utilizes generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality. /li

/ul

p /p

p Job ID: span data-sheets-root= 1 P77545 /span /p div class= content-pay-transparency div class= pay-input div class= description p strong Pay Transparency Notice: /strong The target annual strong base /strong salary for this position can range as detailed below. Total compensation may strong /strong also include equity and bonus eligibility and benefits (including medical, dental, and vision). /p /div div class= title Annual base salary range (excluding equity and bonus): /div div class= pay-range span R$347.900 /span span class= divider /span span R$347.900 BRL /span /div /div /div div class= content-conclusion ul

li style= font-style: italic; font-size: 8pt; strong em Application Limit: /em /strong Candidates may submit a maximum of 3 applications within a 6-month period. /li

li style= font-style: italic; font-size: 8pt; span style= font-size: 8pt; em strong Equal Opportunity Employer: /strong 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. /em /span /li

li style= font-style: italic; font-size: 8pt; span style= font-size: 8pt; em strong US Applicants: /strong View a href= https://www.dol.gov/sites/dolgov/files/WHD/legacy/files/eppac.pdf Employee Rights /a , a href= https://www.eeoc.gov/sites/default/files/2023-06/22-088_EEOC_KnowYourRights6.12.pdf Know Your Rights /a , and a href= https://static-assets.coinbase.com/e-verify.pdf E-Verify /a Notice of Participation. /em /span /li

li style= font-style: italic; font-size: 8pt; span style= font-size: 8pt; em strong Accommodations: /strong 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? a href= https://chromewebstore.google.com/detail/screen-reader/kgejglhpjiefppelpmljglcjbhoiplfn Click here /a to download a free compatible screen reader and view the a href= http://www.chromevox.com/tutorial/ strong /strong tutorial /a . /em /span /li

li style= font-style: italic; font-size: 8pt; span style= font-size: 8pt; em strong Data Privacy Arbitration: /strong By submitting your application, you agree to our a href= https://www.coinbase.com/legal/applicant_privacy_notice Candidate Privacy Notice /a . US applicants: By submitting your application, you agree to a href= https://www.coinbase.com/legal/application-arbitration-agreement Arbitration of Disputes /a . br /em /span /li

/ul

div id= fortidlp-input-element-parent /div /div