AI Engineer Intern - Summer 2027

About Us:
Founded 20 years ago and headquartered in Chicago, the DV Group of financial services firms has grown to more than 600 people operating throughout North America, Europe and Asia. Since spinning out of a large brokerage firm in 2016, DV Trading has rapidly scaled as an independent proprietary trading firm utilizing its own capital, trading strategies, and risk management methodologies to provide liquidity to worldwide financial markets and hedging opportunities to commodity producers and users. Now, DV group affiliates include two broker dealers, a cryptocurrency market making firm, and a bourgeoning investment adviser.

Role Overview:
This is a project-focused internship for an AI engineer embedded on the DevOps team. You will report to the DevOps lead and partner with internal technology teams. The work centers on internal, production-adjacent tooling—not training or shipping customer-facing ML models.

Core Internship Projects:

• Generative assistant for alert response
• Learn our observability stack and what data exists today e.g. Prometheus, Grafana, Loki, Tempo, Alertmanager, OpenTelemetry.
• Prototype a generative agent that uses approved observability sources to propose structured mitigation suggestions for alerts (hypothesis, checks, likely causes, safe next steps), with traceability back to queries, dashboards, or signals where possible.
• Retrieval on internal data (RAG)
• Build and iterate on RAG over permissioned internal data sources (e.g. runbooks, tickets, docs, system design, network design, postmortems) so suggestions and Q&A are grounded and citeable.
• Work with teams to improve coverage and quality of that corpus (metadata, ownership, freshness).
• Path toward agentic remediation (design + scoped implementation)
• Outline how the system could execute approved remediations behind explicit guardrails and human approval.
• Implement only what is allowed and under review—no autonomous production changes without platform sign-off.
• Broader internal Q&A
• Explore how additional internal, permissioned firm data can support natural language questions for engineers.
• Across all phases, permissioning, auditing, logging, and cost controls are non-negotiable requirements, not stretch goals.

Responsibilities:

• Design and prototype agent workflows with tool use, policy boundaries, and human-in-the-loop where appropriate.
• Collaborate with platform and service teams to make more observability and operational context available in a safe, governed way for agents.
• Document experiments, limitations, evaluation approach, and safety assumptions; ship changes via Git (branches, merge requests, meaningful commits).

Requirements:

• Pursuing a BS or MS in Computer Science, Computer Engineering, Information Systems, or a related field
• Expected to graduate by Summer 2028
• Hands-on experience using AI tools (e.g. LLM APIs, assistants, or coding agents) in real projects; preferably experience building an agent (tools, orchestration, or similar—not only prompt-only chat).
• Experience with RAG (retrieval design, chunking, evaluation, grounding, or production-minded prototyping)—including applying it to real or simulated internal/knowledge-base style data, not only public tutorials.
• Python for prototyping and integration; comfortable consuming and creating APIs and working with JSON; able to understand YAML for configs.
• Git workflow: branches, merge requests, meaningful commit messages.
• Strong judgment on data handling: no secrets in prompts/logs, minimize sensitive data, follow internal policies.

Preferred Skills:

• 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).