AI Engineer (Founding Engineer – AI)

TutorAgent and PlannerAgent integrated with Gemini Pro + Pub/Sub messaging.

Redis working memory and Firestore user schema live.

LangSmith evaluation pipeline created with baseline metrics (<15% hallucination rate).

Orchestrate 10+ specialized agents in production.

Reduce TutorAgent response latency <3s end-to-end.

Adaptive learning system live with >40% improvement in learner retention.

AI drift monitoring and guardrails automated in CI/CD.

Research background in NLP, RLHF, or agentic AI systems.

Contributions to open-source AI frameworks.

Prior work on developer-focused AI products.

Startup/founding engineer experience.

Core AI: Google ADK, Gemini Pro, Gemini Vision, Gemini Live API

Communication: Google Cloud Pub/Sub

Memory: Redis (working), Firestore (archival), Neo4j Aura (Developer Graph)

Eval & Prompting: LangSmith, Langfuse, hybrid model router

Infra: Cloud Run, API Gateway, GitHub Actions

Tools: Linear (execution), Notion (PRDs/experiments), GitHub (repos)

Objective: Validate ability to design and implement a production-ready multi-agent system.

Build a TutorAgent that: Takes input: “Teach me React Hooks.” Delegates to sub-agents: CurriculumAgent → outline ContentAgent → lessons CodeAgent → runnable code snippet QuizAgent → quiz JSON Stores all results in Firestore + Developer Graph (Neo4j). Communicates via Pub/Sub.

Takes input: “Teach me React Hooks.”

Delegates to sub-agents: CurriculumAgent → outline ContentAgent → lessons CodeAgent → runnable code snippet QuizAgent → quiz JSON

CurriculumAgent → outline

ContentAgent → lessons

CodeAgent → runnable code snippet

QuizAgent → quiz JSON

Stores all results in Firestore + Developer Graph (Neo4j).

Communicates via Pub/Sub.

Add a Learning Adaptation Loop : If quiz score <60%, regenerate lesson with simplified examples.

If quiz score <60%, regenerate lesson with simplified examples.

Evaluation & Guardrails: Set up LangSmith eval pipeline with at least 20 golden prompts. Implement guardrail filter to block unsafe outputs.

Set up LangSmith eval pipeline with at least 20 golden prompts.

Implement guardrail filter to block unsafe outputs.

Performance Targets: TutorAgent orchestration end-to-end <3s. Sub-agent response <1.5s each.

TutorAgent orchestration end-to-end <3s.

Sub-agent response <1.5s each.

Multi-agent orchestration codebase.

Firestore + Neo4j schema examples.

Evaluation report (accuracy, latency, hallucination rate).

GitHub repo with CI integration.

5-min Loom demo walkthrough.

Architecture & Orchestration Design (30%)

Model Integration & Multimodal Handling (20%)

Evaluation & Guardrails Implementation (20%)

Performance & Scalability (15%)

Documentation & Testing (15%)