Arcadeai

Applied AI Engineer

San Francisco, CA

Sponsorship not specified$179k-$240kDetected 61 days ago

Distributed SystemsMongoDBRedisDatabricksVector DatabasesRESTMachine LearningNLPLLMsAgentic AIMLOpsStatisticsA/B Testing5G/LTEResearch

About the role

The moment an agent accesses customer data, executes a workflow, or makes changes on behalf of a user, authorization, governance, and trust become the real engineering challenge.
Arcade is the MCP runtime that gives agents the power to do both seamlessly.
We connect agents to the systems they act in, then give each one a permission slip and a paper trail - proof of what it's allowed to do, and a record of what it did.

Design and ship agentic tools that go beyond deterministic API wrappers - and define the patterns the rest of the Tools team will use to build more.
Build the agent harness that automates tool creation - take a vendor's API, produce a high-quality toolkit end-to-end, keep humans in the loop only where humans add real value.
Bring applied-ML rigor to tool design - evals, model-aware iteration, retrieval, tool description tuning, response shaping. Make decisions defensible with data.
Set the technical bar for what "good tool-building" looks like as the team scales - your patterns get inherited by every toolkit author after you.
LLM application depth - prompting, retrieval, tool use, agent design. You've built non-trivial agent systems and know where the rough edges are.

5+ years software engineering experience, with at least 2 years shipping production ML or applied-AI systems.
Experience designing or composing multi-tool / multi-agent workflows that produced real outcomes.
You can defend whether a small delta is real or noise.
Comfort across multiple frontier models and reasoning about their behavioral differences.
Comfort with ambiguity - early team, narrow charter that will expand.

call X API with Y arguments, get Z result.
That model breaks down for entire classes of agent work - research a topic, summarize a thread, decide which of three accounts to act on.
When is agentic better than deterministic?
Agents that build tools.
The toolkit catalog is too big for hand-crafting to scale.
There's early work on this already.
Workflows that compose tools.
real actions, on real systems, already shipping inside Fortune 100 companies.
Every AI app needs agentic tools that let AI models take real actions.
Without tools, AI can only chat.
With tools, AI can actually do things.
Think Zapier for AI Actions.

Real deployments with Fortune-100 customers like Morgan Stanley and Open Table
We've assembled authentication, integrations, distributed systems, and AI experts from Okta, Redis, Microsoft, Splunk, Ngrok, Google, Airbyte, Disney, and HPE who've built and founded multiple successful developer platforms.
Design workflows that compose tools into higher-level abstractions customers can actually point at outcomes ("triage this inbox," "close out this account") rather than individual API calls.
If that's the part of the job that makes you nervous, this isn't the right role.
Research is part of the job.

This listing is sourced directly from Arcadeai's careers page and normalized into a canonical job model.