Senior Software Engineer II (AI Enablement)

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Software Engineer II (AI Enablement) based in United States.

The Senior Software Engineer II will build and operate the platform infrastructure that enables organization-wide adoption of AI and agentic technologies. You will own critical systems spanning MCP gateway infrastructure, plugin distribution, model routing, observability, and AI platform tooling. The role combines deep platform engineering with direct business impact, including measurable effects on AI adoption, inference performance, and technology spend. You will work across backend services, developer platforms, security, infrastructure, and AI tooling in a highly collaborative environment. Your work will support both engineers and non-engineers by making agentic capabilities easier, safer, and more scalable to use. This is a hands-on platform role for an experienced engineer who enjoys solving complex problems with real users, operational ownership, and measurable outcomes.

\n

Accountabilities:

• Own and extend the MCP Gateway and connector platform, building and hardening integrations with enterprise systems such as Glean, Slack, Jira, Snowflake, Salesforce, Monday, Tableau, and Databricks.
• Design and maintain authentication, authorization scopes, tenancy, rate limiting, and read/write policy enforcement for connected tools, partnering with Security and platform owners to establish safe-by-default access patterns.
• Own the plugin distribution layer and marketplace publishing pipeline, including versioning, CI/CD, plugin pull request reviews, release hygiene, and developer tooling synchronization.
• Build and maintain shared plugins, skills, hooks, and Spec-Driven Development tooling used across engineering teams.
• Create and maintain authoring documentation and guides that enable other teams to contribute to the platform independently.
• Own platform observability, model gateway configuration, and AI cost attribution, extending telemetry and usage pipelines to measure adoption, tool-call health, and inference spending by team, workload, and model.
• Define model-routing strategies and develop benchmarks and evaluation harnesses that support evidence-based decisions about model selection and performance.
• Extend infrastructure that transforms agent outputs into browsable, searchable, and collaborative experiences, including discovery, tagging, engagement instrumentation, comments, expiration, and sharing notifications.
• Run technical enablement activities such as office hours and educational sessions focused on agentic coding and plugin-authorship practices.
• Mentor engineers on AI platform development patterns, plugin creation, and effective use of agentic coding tools.
• Triage and consolidate incoming platform feature requests and help prioritize improvements based on user needs and platform impact.
• Participate in on-call responsibilities for marketplace-published artifacts and gateway availability.

Requirements:

• Bachelor's degree or higher in Computer Science, Engineering, or a related technical field.
• 5+ years of professional software engineering experience.
• Demonstrated production ownership of a backend service or developer platform, such as an API gateway, service proxy, SDK/CLI, internal developer platform, or comparable system, including responsibility for authentication, releases, and operational health.
• Strong production experience with at least one modern application stack such as Python, TypeScript/Node, Go, or a comparable technology.
• Strong experience with modern CI/CD practices and production software delivery.
• Hands-on experience implementing authentication and authorization for machine-to-machine traffic, including OAuth2, OIDC, M2M credentials, token scoping, and secret management.
• Demonstrated ability to instrument owned systems using metrics, structured logging, tracing, usage analytics, or similar observability practices and use resulting data to inform technical decisions.
• Direct hands-on experience with agentic coding tools such as Claude Code, Cursor, Cody, Copilot agents, Aider, or equivalent tools in production or near-production environments.
• Strong written communication skills, including the ability to create technical documentation, runbooks, and educational resources for engineering teams.
• Experience authoring or maintaining MCP servers, Claude Code plugins, skills, hooks, or comparable LLM-tooling integrations is preferred.
• Experience operating an LLM gateway or inference proxy in production, including routing, fallback, caching, quotas, and cost attribution, is preferred.
• Experience building evaluation harnesses or benchmarks for LLM systems, including A/B comparisons of prompts, tools, or model versions, is a plus.
• Experience operating a package registry, plugin ecosystem, or extension marketplace, including publishing pipelines, semantic versioning, compatibility management, and deprecation processes, is beneficial.
• Background in healthcare technology, HIPAA-regulated environments, or systems handling protected health information is preferred.
• Familiarity with business associate agreements and data-residency considerations for third-party tooling is a plus.
• Experience with technologies such as Python/FastAPI, Vue/TypeScript, Postgres, AWS, Auth0, Datadog, or Sumo Logic is beneficial but not required.
• Comfort working across frontend, backend, and infrastructure boundaries.
• Experience as an early engineer on an internal platform where adoption must be earned through product quality and user value is a plus.
• Strong collaboration, mentoring, problem-solving, ownership, and cross-functional communication skills.
• Ability to work effectively in a remote environment and manage prolonged periods of computer-based work.

Benefits:

• Remote work arrangement within the United States.
• Full-time position with a senior-level platform engineering scope.
• Opportunity to work on AI enablement infrastructure supporting organization-wide adoption of agentic technologies.
• Direct ownership of systems with measurable impact on AI usage, inference costs, model performance, and developer productivity.
• Exposure to advanced technologies including MCP, LLM gateways, agentic coding tools, model evaluation, AI observability, and plugin ecosystems.
• Opportunity to collaborate across engineering, security, infrastructure, and other technical teams.
• Mentoring and knowledge-sharing opportunities through office hours, educational sessions, and engineering enablement initiatives.
• Hands-on ownership of production systems with responsibility for reliability, security, observability, and operational health.
• Opportunity to help shape scalable AI platform standards and tooling in an evolving technical environment.

\n

How Jobgether works:

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

 Why Apply Through Jobgether? 

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1