Description: Join us in building the next generation of AI infrastructure that will power innovation across the customer organization. We’re seeking a full-stack software engineer to support our AI infrastructure team. In this role, you’ll help build and maintain the platform that provides the foundation for the customer’s AI capabilities, with a focus on inference services while supporting a broader ecosystem of AI-enabled applications.
Responsibilities: - Implement and support infrastructure for AI model inference under the guidance of senior engineers.
- Contribute to the development and maintenance of production AI services and applications, including retrieval augmented generation (RAG) and autonomous agents.
- Participate in implementing monitoring, logging, and observability for AI services.
- Assist with automating infrastructure provisioning and configuration using IaC principles.
- Help ensure availability, reliability, and performance of AI platform components.
- Follow established security best practices for AI systems and data.
- Work within ambiguous problem spaces while learning to define structured solutions.
- Collaborate with cross-functional teams and contribute to shared engineering standards.
Skills Requirements: - Experience contributing to production systems.
- Familiarity with high-volume web application architectures.
- Exposure to cloud engineering, preferably AWS.
- Working knowledge of Kubernetes concepts and containerized deployments.
- Proficiency in Python.
- Familiarity with CI/CD pipelines and DevOps practices.
- Ability to learn unfamiliar technologies quickly.
- Strong communication skills and willingness to ask questions.
Nice to Haves: - Exposure to AI inference serving technologies (vLLM, LiteLLM, etc.).
- Familiarity with agentic frameworks (LangChain).
- Awareness of vector databases and embedding systems.
- Interest in distributed systems or performance engineering.
|