Job Title: AI/ML Engineer
Location: Anywhere in US (Hybrid)
Duration: 12+ Months
JD
The AI Platform and Services team builds the shared services, SDKs, workflows, and guardrails that help product teams deliver trustworthy GenAI features. Our platform includes inference, VectorDB/RAG, evaluation and observability integrations, MCP services, agentic capabilities, and self-service onboarding workflows.
You will help build and operate AI services including Galileo, AI Defense, Agent Registry, and Agent Memory, while automating the developer workflows used to onboard models and services. This role combines backend service development, integration engineering, developer experience, and production ownership.
Your Impact
- Build, integrate, test, deploy, and operate Galileo, AI Defense, Agent Registry, and Agent Memory.
- Create reusable service patterns for CI/CD, configuration, secrets, authentication, authorization, telemetry, health checks, upgrades, backups, and rollback.
- Automate self-service model onboarding from intake and QA through compatibility checks, provisioning, canary deployment, provenance, and production readiness.
- Integrate onboarding workflows with Jira, Slack, surveys or request forms, and tracking dashboards so requesters and operators have clear status and ownership.
- Develop APIs, SDK integrations, templates, and documentation that reduce one-off work for product teams adopting AI platform services.
- Implement evaluation, safety, and observability integrations using Galileo, LangSmith, or comparable platforms.
- Support RAG, VectorDB, agentic, and MCP-based use cases, including secure integration with internal services and tools.
- Add automated tests, dashboards, alerts, runbooks, and operational readiness checks before services enter production.
- Participate in production support, debugging, incident response, and post-incident improvements.
- Create maintainable code, documentation, service templates, and reusable operational automation.
Minimum Qualifications
- Bachelor’s degree in computer science, engineering, or equivalent practical experience.
- 4+ years of hands-on experience building and operating backend services, platform integrations, or developer tooling.
- Strong proficiency in Python, Go, Java, or a comparable backend language.
- Experience building production REST or gRPC services and working with containers, Kubernetes, CI/CD, configuration, and secrets management.
- Experience integrating multiple services or APIs and diagnosing failures across system boundaries.
- Experience with automated testing, observability, dashboards, alerts, runbooks, and production readiness.
- Strong communication and collaboration skills across platform and product teams.
Preferred Qualifications
- Experience with RAG systems, VectorDBs, embeddings, document ingestion, retrieval, metadata, ranking, or retrieval evaluation.
- Practical experience with LangChain, LangGraph, Semantic Kernel, or similar agentic frameworks.
- Experience integrating MCP servers or other tool ecosystems with internal and external APIs.
- Familiarity with LangSmith, Galileo, or comparable evaluation, tracing, safety, or guardrail platforms.
- Experience building developer platforms, SDKs, templates, onboarding portals, workflow automation, or self-service systems adopted by multiple teams.
- Familiarity with model deployment, compatibility checks, canary rollout, provenance, and evaluation workflows.
- Experience with identity, authorization, policy enforcement, auditability, and secure multi-tenant services.
What Success Looks Like
- AI services are delivered with automated deployment, rollback, health checks, security controls, telemetry, and operational readiness.
- Model and service onboarding uses a repeatable, trackable self-service workflow instead of manual intake and one-off coordination.
- Reusable service automation reduces ongoing deployment, upgrade, security, and incident-response effort.
- Product teams can adopt supported AI services through clear APIs, SDKs, templates, documentation, and support boundaries.
