SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Aledade is seeking a Senior Software Engineer II to help build and operate the shared AI Core Platform infrastructure that enables applications and AI agents across the organization to securely and reliably access foundation models.
In this role, you will work on platform capabilities including model gateways, cloud AI services, provider integrations, routing and fallback mechanisms, usage controls, observability, reliability, and model governance. You will think beyond individual features to consider the full lifecycle of production platform systems: architecture, scalability, failure modes, security, observability, operational readiness, cost, and developer experience.
Key responsibilities include:
- Develop and implement scalable and performant solutions for the AI platform
- Partner as a peer with Engineering Managers, Product Managers, and stakeholders to develop and execute technical roadmaps using Agile processes
- Mentor and coach junior engineers, including thorough pull request reviews and receptiveness to critical feedback
- Help evolve the platform as AI adoption grows across Aledade, building reusable and self-service capabilities rather than one-off solutions
- Work closely with engineers, product partners, security, and infrastructure teams
You will operate in ambiguous problem spaces, make pragmatic technical decisions, and build secure, maintainable, observable, and resilient systems.
REQUIREMENTS:
- BS/BTech or higher in Computer Science, Engineering, or related field
- 6+ years experience as an engineer building full-stack web applications as part of a cross-functional team
- 3+ years experience working with SQL or other database querying language on large multi-table data sets
- 3+ years experience acting as a trusted technical decision-maker in a team setting, solving for short-term and long-term business value
- 3+ years experience coaching other engineers
PREFERRED EXPERIENCE:
- Building or operating production platform infrastructure, distributed systems, developer platforms, or high-availability shared services
- LLM infrastructure, model gateways, foundation model APIs, or managed AI platforms (AWS Bedrock, Azure OpenAI, Google Vertex AI, or similar)
- Cloud infrastructure (preferably AWS) and technologies such as Kubernetes, containers, and infrastructure as code
- Designing observability and operational practices for production systems (metrics, distributed tracing, logging, alerting, SLOs, dashboards, failure handling)
- Designing APIs and self-service platform capabilities for other engineering teams
- Identity, access control, secrets management, security, and governance for shared infrastructure
- Cost management, usage attribution, quotas, budgets, or capacity management for shared platforms
- Operating systems handling sensitive or regulated data
- Evaluating architectural tradeoffs across reliability, performance, security, cost, scalability, and developer experience
