Senior Software Engineer, AI Engineering

Mercury is a company making a deliberate, company-wide bet on AI, aiming to transform scattered AI experiments into shared infrastructure, shared context, and shared capabilities to accelerate innovation.

Introduction

Mercury is making a deliberate, company-wide bet on AI. As a Senior Software Engineer in AI Engineering, you will join a team focused on building and scaling Mercury's internal AI platform and enablement layer. Your work will transform scattered AI experiments into shared infrastructure, context, and capabilities, multiplying the velocity of all AI efforts within the company.

Responsibilities

Extend the AI platform foundation

• Build and evolve MCP servers to connect internal systems and data sources into a coherent interface for agents and engineers.
• Expand and operate the LLM gateway infrastructure, including routing, rate limiting, cost attribution, and observability across teams.
• Convert early patterns into durable defaults, such as shared prompt libraries, guardrails, and policy-as-code, enabling teams to innovate safely.

Strengthen the shared company knowledge layer

• Shape and maintain structured context artifacts that are clean, reliable, and agent-consumable, allowing LLMs to reason accurately about Mercury's domain.
• Improve internal knowledge discoverability and retrieval, helping both humans and agents find accurate answers quickly.
• Partner with domain teams to standardize key sources of truth and ensure they remain current.

Enable faster prototyping and iteration across the company

• Build and refine sandbox environments and tooling for safe and rapid AI experimentation.
• Create self-service scaffolding for non-engineers (PMs, ops, finance) to prototype and deploy AI-powered workflows with minimal support.
• Develop playgrounds and evaluation harnesses to test and iterate internal AI agents in controlled environments before production deployment.

Requirements

• 5+ years of backend development experience in complex, production systems, with a track record of building engineer-dependent technologies.
• Fluency across programming languages and the ability to navigate platform engineering, infrastructure, and developer tooling.
• Hands-on experience building LLM-powered systems (RAG pipelines, agents, eval frameworks) and having shipped at least one to production.
• Understanding of real-world tradeoffs in AI deployments, including cost modeling, observability, latency, and safety.
• High-agency and self-directed, capable of operating effectively without tightly defined scope, identifying high-leverage work, and executing it.
• Clear communication skills for both technical and non-technical audiences, able to explain creations and their significance.

Benefits

The total rewards package at Mercury includes base salary, equity, and benefits. Salary and equity ranges are highly competitive within the SaaS and fintech industry, regularly updated with reliable compensation survey data for the industry. New hire offers are based on experience, expertise, geographic location, and internal pay equity relative to peers.

About Company

Mercury is a company making a deliberate, company-wide bet on AI, aiming to transform scattered AI experiments into shared infrastructure, shared context, and shared capabilities to accelerate innovation.

How to Apply

Please apply through the provided application link.