Senior Software Engineer - AI Engineering
AI summary of the role
Mercury is building an internal AI platform and enablement layer to turn scattered AI experiments into shared infrastructure, context, and capability.
What you’ll do
- Build and evolve MCP servers that connect internal systems and data sources into a coherent interface for agents and engineers.
- Expand and operate LLM gateway infrastructure: routing, rate limiting, cost attribution, and observability across teams.
- Shape and maintain structured context artifacts so LLMs can reason accurately about Mercury's domain.
- Build sandbox environments and self-service scaffolding so engineers and non-engineers can prototype and deploy AI workflows.
What you’ll bring
- 5+ years of backend development experience in complex, production systems.
- Fluent across programming languages and experienced in platform engineering, infrastructure, and developer tooling.
- Hands-on experience building LLM-powered systems (RAG pipelines, agents, eval frameworks) with at least one production deployment.
- Understands tradeoffs in AI deployments: cost modeling, observability, latency, and safety.
Technologies
MCP servers · LLM gateway · RAG pipelines · agents · eval frameworks · prompt libraries · guardrails · policy-as-code · sandbox environments · developer tooling
About Mercury
Banking and financial-operations platform built for startups and small businesses, offering checking, savings, treasury, credit cards, bill pay, venture debt, and payroll.
Series C
Source and classification
Internal deployment & tooling · Evidence for this classification:
In 1600, William Gilbert published De Magnete—the first systematic study of magnetism. He didn't just theorize; he built instruments, ran experiments, and shared what he learned so that others could go further. Three centuries later, those foundations helped power the modern world. At Mercury, we're making a deliberate, company-wide bet on AI. Frontier users are already pushing boundaries—building agents, automating workflows, moving fast. But they're doing it in silos. This role exists to change that: to take those scattered experiments and turn them into shared infrastructure, shared context, and shared capability. The goal is a multiplier effect—where the most ambitious AI work inside Mercury lifts the velocity of everyone else. What you'll do You'll join a team that has already started building Mercury's internal AI platform and enablement layer. Your work will be to extend,
More from the job description
In 1600, William Gilbert published De Magnete—the first systematic study of magnetism. He didn't just theorize; he built instruments, ran experiments, and shared what he learned so that others could go further. Three centuries later, those foundations helped power the modern world. At Mercury, we're making a deliberate, company-wide bet on AI. Frontier users are already pushing boundaries—building agents, automating workflows, moving fast. But they're doing it in silos. This role exists to change that: to take those scattered experiments and turn them into shared infrastructure, shared context, and shared capability. The goal is a multiplier effect—where the most ambitious AI work inside Mercury lifts the velocity of everyone else. What you'll do You'll join a team that has already started building Mercury's internal AI platform and enablement layer. Your work will be to extend, harden, and scale what's in motion, and to help partner teams adopt it. Extend the AI platform foundation Build and evolve MCP servers that connect internal systems and data sources into a coherent interface for agents and engineers. Expand and operate our LLM gateway infrastructure: routing, rate limiting, cost attribution, and observability across teams. Turn early patterns into durable defaults: shared prompt libraries, guardrails, and policy-as-code so teams can move fast safely. Strengthen [... source excerpt omitted ...] powered workflows with minimal hand-holding. Build playgrounds and evaluation harnesses so internal AI agents can be tested and iterated in controlled environments before hitting production. This list is illustrative. Priorities will shift as we learn; the right person will help choose the next highest-leverage work. The ideal candidate Has 5+ years of backend development experience in complex, production systems—you've built things that other engineers depended on. Is fluent across programming languages and can navigate platform engineering, infrastructure, and developer tooling without needing a map. Has hands-on experience building LLM-powered systems—RAG pipelines, agents [... source excerpt omitted ...] ovey as part of our hiring and / or promotional process for jobs in NYC and certain features may qualify it as an AEDT. As part of the evaluation process we provide Covey with job requirements and candidate submitted applications. We began using Covey Scout for Inbound on January 22, 2024. [Please see the independent bias audit report covering our use of Covey for more information.] #LI-ES1
Employer postings · Data from · Sources