About this role
The day-to-day work for this AI Engineer Intern involves focusing on internal, production-adjacent tooling within the DevOps team. The intern will partner with internal technology teams to develop and prototype features that enhance operational context for agents, rather than focusing on training or deploying customer-facing machine learning models. Key projects include building a generative assistant for alert responses and prototyping agents that use observability data to suggest structured mitigation steps for alerts, complete with traceability. A significant part of the work involves implementing Retrieval Augmented Generation (RAG) over permissioned internal data sources, such as runbooks and system designs, to ensure suggestions are grounded and citeable. The intern will also contribute to improving the quality and coverage of this internal data corpus.
This internship exists to provide hands-on experience in building reliable, governed AI systems within a financial services environment. The focus is on operational intelligence and internal knowledge management, ensuring that any agentic remediation actions adhere strictly to defined guardrails and require human approval before execution. The role is ideal for a candidate who enjoys bridging the gap between AI capabilities and robust operational infrastructure.
An individual who excels at prototyping agent workflows, understands the importance of auditing and logging, and prioritizes safety and permissioning would thrive in this role. This position is suited for a student looking to gain practical experience in applying LLMs to complex, regulated operational challenges.
What you will do
- Design and prototype agent workflows incorporating tool use, policy boundaries, and human-in-the-loop mechanisms.
- Collaborate with platform and service teams to make observability and operational context available to agents in a safe and governed manner.
- Document all experiments, limitations, evaluation approaches, and safety assumptions thoroughly.
- Manage changes through standard Git workflows, including branches, merge requests, and meaningful commit messages.
- Implement features strictly adhering to established permissions and review processes.
- Explore how additional internal, permissioned firm data can support natural language queries for engineers.
- Outline the design for executing approved remediations behind explicit guardrails and human approval.
What you need
- Must be pursuing a BS or MS in Computer Science, Computer Engineering, Information Systems, or a related field.
- The candidate is expected to graduate by Summer 2028.
- Possesses hands-on experience using AI tools, such as LLM APIs or coding agents, in real projects, with a preference for experience building agents (tools, orchestration, or similar).
- Requires experience with RAG, including design, chunking, evaluation, grounding, or production-minded prototyping applied to internal knowledge bases.
- Proficiency in Python is necessary for prototyping and integration, including comfort with APIs, JSON, and YAML configurations.
- Demonstrates a solid understanding of Git workflows, including managing branches, merge requests, and detailed commit messages.
- Must possess strong judgment regarding data handling, ensuring no secrets are present in prompts or logs and adherence to internal policies.
Nice to have
- Linux fundamentals (shell, processes, logs, permissions, basic troubleshooting)
- Networking basics (DNS, TCP/HTTP/S, ports, load balancing vs Ingress at a conceptual level)
- Kubernetes fundamentals (debugging, pods, services, ingress)
- Coursework or projects involving Kubernetes, Prometheus/Grafana, OpenTelemetry, CI/CD, Terraform/Ansible, or cloud (AWS/GCP/Azure)
Benefits
- $40.00-$50.00 per hour
Skills and tech stack
Questions candidates ask
What is the remote policy for this internship?
The posting does not specify a remote work policy for this internship role.
What is the compensation for this internship?
The compensation range for this internship is $40.00-$50.00 per hour.
What is the primary technology stack used for this role?
The tech stack includes Python for prototyping, JSON, YAML for configurations, and various observability tools like Prometheus, Grafana, Loki, Tempo, and OpenTelemetry.
What is the team structure like?
The AI Engineer Intern will report directly to the DevOps lead and will partner with internal technology teams.