Sr. AI Engineer - Engineering Enablement

Silversmith Capital Partners; United States; On-site; USD 150,000 - 220,000; Full time

Job summary

MeridianLink is seeking a Senior Engineer on the Engineering Enablement team to own and advance the shared CI/CD infrastructure, AI development tooling, and sandbox environments used by hundreds of R&D engineers. You will drive adoption of the AI-native development program, build harnesses and agent infrastructure, and ship real, production-ready features.

This is a hands-on role with real code and infrastructure, partnering with engineering teams to accelerate delivery and improve reliability.

Qualifications

• 5+ years of professional software engineering delivering features and infrastructure in production.
• Hands-on experience building and maintaining CI/CD systems at org scale (GitLab CI and/or Jenkins).
• Experience building developer-facing tooling or platform services relied on by engineers.
• Hands-on experience with LLM developer tooling: MCP, LLM APIs, agent orchestration, or AI harnesses.
• Proficiency in Python or TypeScript with production-grade ownership.
• Proficiency with Kubernetes and Helm at production scale on AWS or Azure.
• Experience designing shared pipeline abstractions and CI/CD infrastructure used by multiple teams.
• Familiarity with infrastructure-as-code tools (Terraform, Pulumi).
• Proficiency with Git, Docker, automated testing, and modern scripting languages.
• Active daily use of AI-assisted development tools.
• Bachelor's degree in Computer Science, Software Engineering, or equivalent experience.

Responsibilities

• Own and evolve CI/CD and AI tooling platforms end-to-end across multiple teams.
• Identify edge cases and failure modes within assigned scope.
• Participate in code reviews with constructive feedback and early blockers surfaced.
• Design pipeline abstractions that balance standardization with flexibility at scale.
• Mentor engineers and contribute to documentation and onboarding.

Skills

CI/CD Systems

Python

Kubernetes

LLM Tooling

Developer Infra

Code Reviews

Education

Bachelor's degree in CS or equivalent

Tools

GitLab CI

Jenkins

Terraform

Pulumi

Docker

Job description

Position Summary

This is a senior-level individual contributor on the Engineering Enablement team. The team builds the shared CI/CD infrastructure, AI development tooling, and sandbox environments that hundreds of R&D engineers depend on. A core part of that mission is advancing MeridianLink's AI-native development program — building the harnesses, agent infrastructure, and shared tooling that move engineering teams from ad-hoc AI usage toward autonomous, repeatable development pipelines. This role owns a significant chunk of that platform and drives adoption across engineering teams.

This is a hands‑on role: real code, real infrastructure, direct engagement with engineering teams. The measure of success is how much faster you make everyone else.

Key Competencies

What it means to be a Senior Engineer at MeridianLink

Senior individual contributors own their work end‑to‑end, identify problems before they're surfaced, and make the engineers around them better. Senior engineers at MeridianLink are active, daily users of AI‑assisted development tools.

Technical Execution & Delivery

• Owns features and infrastructure end‑to‑end: design through production release, limited guidance required
• Identifies edge cases and failure modes independently within assigned scope
• Participates actively in code review with constructive, specific feedback
• Surfaces blockers early rather than waiting for check‑ins

Craft & Professionalism

• Writes tests that catch regressions without over‑engineering the suite
• Monitors shipped work, responds to issues, and follows incidents to resolution
• Puts institutional knowledge into shared systems rather than individual heads

CI/CD & Build Systems

• Designs pipeline abstractions (templates, shared jobs, reusable configs) that work across multiple teams and tech stacks
• Reasons clearly about the tradeoffs between standardization and flexibility at org scale
• Keeps pipelines healthy, observable, and continuously improving

AI Tooling & Developer Infrastructure

• Builds and maintains shared MCP servers, agent orchestration harnesses, and reusable skills and plugins
• Understands LLM developer tooling in practice: tool definitions, agent loops, prompt management
• Designs shared tooling with product thinking: requirements gathering, feedback triage, prioritized backlog

Sandbox & Agent Infrastructure

• Owns the shared infrastructure layer for autonomous AI agent environments: orchestration, provisioning, observability, cost controls, and security guardrails
• Partners with product teams on their individual sandbox configs while maintaining the platform underneath

Enablement & Engineering Advocacy

• Treats engineers as customers: office hours, documentation, feedback loops
• Measures platform impact with DORA metrics, adoption rates, and time‑to‑productivity data
• Closes the gap between shipping tooling and driving adoption

Expected Duties

CI/CD Platform

• Own and evolve shared infrastructure: templates, shared jobs, abstractions, and standards across R&D
• Resolve systemic reliability issues: flaky tests, slow builds, caching inefficiencies
• Partner with teams during migrations and help them adopt shared abstractions without disrupting delivery

AI Tooling Platform

• Build and maintain shared MCP server infrastructure connecting AI harnesses to internal systems (Jira, Confluence, GitLab, internal APIs)
• Develop agent orchestration infrastructure: scheduling, observability, cost controls, security boundaries
• Build reusable harness skills, slash commands, and workflow scripts that ship as internal plugins

Sandbox Infrastructure

• Own the shared infrastructure for AI agent sandbox environments: container orchestration, environment templates, networking, resource management
• Build and maintain orchestration and admin tooling: provisioning, lifecycle management, health monitoring, cost tracking
• Implement security guardrails for data isolation between sandbox environments

Enablement & Adoption

• Drive AI tooling adoption through documentation, onboarding programs, office hours, and direct team engagement
• Maintain the internal best practices hub and AI development playbook
• Instrument platform usage and productivity metrics to measure whether investments are moving the needle

Collaboration & Growing Others

• Participate in design discussions and code reviews; give and receive feedback constructively
• Mentor other engineers on the team
• Contribute to documentation and onboarding materials that reduce tribal knowledge

Qualifications: Knowledge, Skills, and Abilities

Required

• 5+ years of professional software engineering experience, delivering features and infrastructure independently in production
• Hands‑on experience building and maintaining CI/CD systems at org scale, preferably GitLab CI and/or Jenkins
• Experience building developer‑facing tooling or platform services other engineers depend on
• Hands‑on experience with LLM developer tooling: MCP, LLM APIs, agent orchestration, or AI harnesses (Claude Code, Cursor, Copilot Workspace, or equivalent)
• Deep proficiency in Python or TypeScript, with production experience sufficient to own and deliver real features
• Proficiency with Kubernetes and Helm at production scale on AWS or Azure
• Experience designing shared pipeline abstractions and CI/CD infrastructure used by multiple teams
• Familiarity with infrastructure‑as‑code tools (Terraform, Pulumi, or equivalent)
• Proficiency with standard development tooling: Git, Docker, automated testing, and modern scripting languages
• Active daily use of AI‑assisted development tools
• Bachelor's degree in Computer Science, Software Engineering, or equivalent experience

Preferred

• Prior Engineering Enablement, Platform Engineering, or Developer Productivity role with direct measurement of developer velocity
• Experience building MCP servers or tool‑integration layers for LLM‑based systems
• Experience building or operating infrastructure for autonomous AI agents: sandboxed execution, scheduling, observability, cost management
• Familiarity with DORA metrics and developer productivity instrumentation
• Experience with JFrog Artifactory, Nexus, or equivalent artifact management systems
• Prior experience in financial services, fintech, or a regulated technology environment
• Exposure to SOC 2 or similar compliance frameworks from an engineering perspective

What Success Looks Like

Within the first few months, a successful hire is shipping CI/CD improvements teams are actively using and contributing meaningfully to the AI tooling platform. Over time, success is adoption: more teams on shared infrastructure, faster delivery, less one‑off tooling being built in isolation. Engineers who thrive here care about making other people more productive and find genuine satisfaction in watching adoption metrics climb.