← All roles

Senior Software Engineer - Mercury Command

Mercury· Engineering
Apply on company site
Hybrid (San Francisco, CA), Hybrid (New York, NY), Hybrid (Portland, OR), Remote$200.7k - $250.9kfull-timePosted 8mo ago

About the role

Senior Software Engineer focused on Mercury Command, an LLM-powered financial assistant. Responsible for designing and shipping new Command capabilities, owning the LLM layer, building quality evals, and ensuring reliability and safety in production. Remote-friendly across the US, Canada, or multiple US cities.

Responsibilities

  • Design and ship new Command skills, the domain-specific instruction sets that teach the model how to handle workflows like sending money, managing invoices, and understanding cash flow
  • Design and build agentic workflows in Command, defining the architecture for how multi-step agent interactions should work as we extend what the product can do on a customer’s behalf
  • Work with backend teams to define tool schemas for new capabilities, shaping the data contracts between Mercury's business logic and the model
  • Own new capabilities end to end, from the system prompt to the frontend component that renders the response
  • Maintain and evolve Command's prompt architecture: the system prompt, skill loading system, session context, and the policy and compliance layers underneath
  • Tune model behavior: reasoning effort, prompt caching strategy, fallback chains, and the streaming patterns that make the product feel fast
  • Stay current with how models are evolving and bring that knowledge back to how Command is built
  • Write and expand Command's eval harness, adding cases that cover new capabilities and scoring rubrics that detect regressions
  • Partner with product and compliance teams to define what 'working correctly' means for each new capability, then build the tests that prove it
  • Own the reliability and quality of what you ship, from initial design through post-launch monitoring

Qualifications

  • Has 7 or more years of software engineering experience, with deep technical expertise building and scaling LLM-powered applications in production
  • Experience designing agentic systems and architecting multi-step workflows that are reliable, explainable, and safe to run on behalf of real users
  • Built eval infrastructure and can write cases that measure product effectiveness beyond plausible model outputs
  • Understands tradeoffs in LLM deployments: latency, cost, compliance, and production failure modes
  • Has opinions about trustworthy AI products and can contribute toward that bar
  • Comfortable with TypeScript and willing to learn Haskell for backend tool work, or already comfortable with both
  • Can work across the full stack of an AI product, from the system prompt to the streaming frontend
  • Track record of mentoring engineers and raising the technical bar of their team

Skills

Required:LLM-powered application designAgentic systems designEval infrastructureTypeScript
Nice to have:Haskell (backend tool work)

Benefits

  • Total Rewards: base salary, equity (stock options/RSUs), and benefits
  • Competitive salary and equity ranges
  • Discretionary bonuses may vary per location
Last updated Aug 26, 2026. Interested? Apply on the company site.
Mercury logo

About Mercury

Online Business Banking For Startups & Small Businesses | Financial Workflows

Powerful banking. Simplified finances. Apply in 10 minutes for business banking that transforms how you operate.

bankingfinancial workflowsbusiness bankingmobile bankingcorporate cardscredit cardsdeposit insurancetreasury
Company profileWebsite

More open roles at Mercury