DeveloperJobs.io
← Back to all jobs

Job Description

Mercury.com is seeking a Senior Software Engineer focused on AI Engineering to extend and harden its internal AI platform. This role centers on strengthening the shared knowledge layer and enabling faster AI prototyping across the company, with onsite work in New York. The position offers a competitive annual salary range and an opportunity to shape how teams leverage AI at scale.

Location: New York, NY (onsite) • Salary: USD 166,600 - 218,700 per year

Responsibilities

  • Develop and enhance MCP servers that unify internal systems and data sources into a consistent interface used by agents and engineers.
  • Scale and operate the LLM gateway infrastructure, covering routing, rate limiting, cost attribution, and cross-team observability.
  • Convert early patterns into durable defaults, including shared prompt libraries, guardrails, and policy-as-code to support fast yet safe team work.
  • Design and maintain structured context artifacts that are clean, reliable, and usable by agents to enable accurate domain reasoning by LLMs.
  • Improve internal knowledge discovery and retrieval so both humans and agents locate accurate answers quickly.
  • Collaborate with domain teams to standardize key sources of truth and keep them current.
  • Build and refine sandbox environments and tooling that allow engineers to experiment with AI safely and efficiently.
  • Develop self-service scaffolding so non-engineers such as PMs, operations, and finance can prototype and deploy AI-powered workflows with minimal assistance.
  • Create playgrounds and evaluation harnesses to test and iterate internal AI agents in controlled environments before production.

Requirements

  • 5+ years of backend development experience in complex, production systems, delivering components that other engineers rely on.
  • Fluency across multiple programming languages and comfort with platform engineering, infrastructure, and developer tooling.
  • Hands-on experience building LLM-powered systems—RAG pipelines, agents, or evaluation frameworks—and production-shipped implementations.
  • A practical understanding of AI deployment tradeoffs, including cost modeling, observability, latency, and safety.
  • High initiative and self-direction, able to operate with loosely defined scope and identify high-leverage work to complete.
  • Clear communication across technical and non-technical audiences, explaining what was built and why it matters.

Similar Jobs