Senior Software Engineer - AI Engineering

Based in New York, this onsite Senior Software Engineer - AI Engineering role offers a salary range of USD 166,600 to 218,700 per year. You will help extend, harden, and scale Mercury's internal AI platform, strengthen the shared knowledge layer, and accelerate AI prototyping across the organization.

Responsibilities

• Develop and evolve MCP servers that unify internal systems and data sources into a coherent interface for agents and engineers.
• Scale and operate the LLM gateway infrastructure, including routing, rate limiting, cost attribution, and cross-team observability.
• Turn early patterns into durable defaults with shared prompt libraries, guardrails, and policy-as-code to enable fast and safe progress.
• Define and maintain structured context artifacts that are clean, reliable, and agent-friendly so LLMs can reason accurately about Mercury's domain.
• Improve internal knowledge discoverability and retrieval so both humans and agents can quickly access accurate answers.
• Collaborate with domain teams to standardize key sources of truth and keep them current.
• Create and refine sandbox environments and tooling that allow engineers to experiment with AI safely and efficiently.
• Build self-service scaffolding so non-engineers such as PMs, ops, and finance can prototype and deploy AI-powered workflows with minimal hand-holding.
• Develop 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 depend on.
• Fluent across programming languages with the ability to navigate platform engineering, infrastructure, and developer tooling independently.
• Hands-on experience building LLM-powered systems such as RAG pipelines, agents, or evaluation frameworks, with at least one delivering to production.
• Strong understanding of AI deployment tradeoffs including cost modeling, observability, latency, and safety.
• High initiative and self-direction, capable of autonomous work with limited scope and high-leverage outcomes.
• Clear communication across technical and non-technical audiences, explaining what was built and why it matters.