Applied AI Engineering Intern

Posted 21d ago

The employer’s full description could not be read from their board. This is a summary of the posting — follow the apply link for the original.

Add a data source end to end: the tool that reads it, the skill that teaches the agent to use it, and the eval that checks the answers
Extend the orchestration layer: scheduled runs, durable multi-step workflows, delivery back into Slack
Extend the eval layer: grounded checks, validating the LLM judge against human labels, per-workflow token metering
Move a rule out of the standing prompt into a tool and show the prompt got shorter
Work with a senior engineer on the isolation and credential boundary

Built an LLM agent with tool use and multi-step turns that ran for real users
Python and Rust
Linux, Docker, git, and Kubernetes: NetworkPolicy, Helm, pod lifecycle
Postgres as a durable state store: transactions, idempotent writes, checkpoint and replay
Claude Code and the Anthropic API: tool definitions, skills, prompt caching, and how a harness loop is driven from a CLI
Understand why an agent should hold a placeholder instead of a key, why a keyword match over live answers is not an eval, and why an LLM judge is unvalidated until a human grades a sample of its verdicts
Prefer small, verified changes to rewrites, and write them so someone who was not there can follow the reasoning

Contributions to an open-source agent runtime or coding-agent harness
Built a Slack app: Events API, request signing, delivery of long-running replies
Security engineering at a network boundary: TLS-intercepting proxies, credential injection, egress allowlists
Published research or serious independent work on agent evaluation or multi-agent coordination
Trading systems: PnL, ledgers, positions, funding, and why a figure is relayed from the system that owns it

Skills