CoinbaseHiring

Staff Software Engineer, Backend (Agentic Trading)

  • USD 218,025 to 256,500 per year
  • Remote, United States
  • Senior
  • Posted 13 days ago
In one line

Staff backend role on a small full-stack team building an AI trading advisor inside a consumer finance app; remote, with quarterly in-person sessions.

Staff Software Engineer, Backend (Agentic Trading) is a senior remote role in the United States at Coinbase. Pay: USD 218,025 to 256,500 per year. Posted 6 Nov 2026. Key requirements: five or more years in software engineering, with deep backend work and a record of; go skills, or a clear ability to pick it up fast; hands-on experience with production LLM or agent systems, such as tool calling.

About the role

Remote-first with quarterly team gatherings. The services you own carry advice and trade execution for millions of customers, so speed, clarity and auditability matter as much as shipping.

At a glance

Pay
USD 218,025 to 256,500 per year
Remote scope
Remote, United States
Seniority
Senior
Experience
At least 5 years
Skills
Go, API design, Distributed systems, Data modeling, Tool calling, Prompt engineering, Evals
Posted
6 Nov 2026
Last checked
19 Nov 2026

What you will do

  • Own the backend services behind the AI advisor and user strategies, from design to launch and running them in production
  • Wire trading APIs so agent suggestions and user strategies turn into correct, auditable trades
  • Build the agent use: tool calling, orchestration, saved state and recovery from failed or half-finished actions
  • Tune agent behavior using prompt work, evals and conversation review, working with a registered adviser on advice changes
  • Improve reliability, latency, tracing and execution safety, including retries and guards against duplicate actions

What they look for

  • Five or more years in software engineering, with deep backend work and a record of shipping and running production services
  • Go skills, or a clear ability to pick it up fast
  • Hands-on experience with production LLM or agent systems, such as tool calling, orchestration or evaluation
  • Able to take vague projects from nothing to production with little supervision and good judgment

How Keywordise applies for you

  1. 1Upload your CVAdd your CV once. It takes about a minute.
  2. 2Tailored to this jobKeywordise writes a CV and a cover letter for this job from your real experience.
  3. 3The form fills itselfName, email, experience and screening questions, field by field.
  4. 4Application sentYou get a receipt and follow it in your dashboard.

Apply with Keywordise AI7-day free trial, no card.

Apply from your AI assistant

Connect Keywordise to your assistant once, then send it the prompt. It applies for you.

Claude

  1. In Claude, open Settings, then Connectors, and choose Add custom connector.
  2. Name it Keywordise and paste the connector URL.
  3. Click Connect, log in to Keywordise and approve. Then send the prompt in a new chat.
Connector URL
https://keywordise.com/mcp

Disconnect any time in your Keywordise settings.

ChatGPT

  1. In ChatGPT, open Settings, then Connectors. On plans that need it, turn on developer mode first.
  2. Add a new connector with the connector URL and choose OAuth. Leave the client ID and secret empty.
  3. Log in to Keywordise and approve. Then send the prompt in a new chat.
Connector URL
https://keywordise.com/mcp

Disconnect any time in your Keywordise settings.

Muse

  1. Open Muse (muse.ai or the app) and send it the message below.
  2. If Muse asks how to sign in, answer OAuth. Open the sign-in link it sends, log in to Keywordise and approve.
  3. Send the prompt. Muse asks before it sends anything.
Message for Muse
Add a custom connector called Keywordise. It is a remote MCP server at https://keywordise.com/mcp and uses OAuth. Give me the sign-in link.

Muse is available in the US only for now.

Prompt
Apply to Keywordise job mtybfgzeo4
How to connect

Questions about this job

Can I do this job remotely, and from which countries?

Yes. The posting lists Staff Software Engineer, Backend (Agentic Trading) as a remote role for candidates in the United States.

What does this job pay?

The posting states USD 218,025 to 256,500 per year.

What experience is needed?

It is a senior role. The posting asks for: five or more years in software engineering, with deep backend work and a record of shipping and running production services; go skills, or a clear ability to pick it up fast; hands-on experience with production LLM or agent systems, such as tool calling, orchestration or evaluation. Skills it names include Go, API design, Distributed systems, Data modeling.

How do I apply with Keywordise AI?

Select Apply with Keywordise AI, sign up and upload your CV. Keywordise writes a CV and a cover letter for this job from your real experience and applies for you. The 7-day free trial needs no card.

More remote IT and software jobs

All remote IT and software jobs
CoinbaseRemote, United States
Apply with Keywordise AI