Senior Agentic AI Engineer

Summary
We're hiring a senior Agentic AI Engineer on a project-based engineer to audit, architect, and harden our production personalization engine. You'll work directly with our Head of Product and engineering team to take working prototypes to production-ready quality before November 2026.

Estimated 30–60 hours per month, ~3 months, with the possibility of extension.

We're building a career-intelligence and upskilling platform serving learners across MENA and Africa. We deliver outcomes — completed cohorts, secured placements, career progression — for government training contracts, university partnerships, and large-employer partnerships.

What you'll do:
We've prototyped a personalization engine on top of our new Learn app. The basic framework exists to validate the concept; we want a senior engineer to make it production-grade. Specifically:

1. Architecture audit
   Review the personalization engine end-to-end: - Zone 1 — Surfaces: homepage canvas, in-course chat, events / jobs / comms cards - Zone 2 — Agents: LangGraph supervisor + vertical agents (Courses, Events, Jobs, Comms) - Zone 3 — Backends: MongoDB Atlas vector store, course content + transcript ingestion, employer pipeline, PostHog telemetry - Zone 4 — Self-improvement loop: scoring agent → user.md → tuned routing

2. RAG / retrieval design review

3. Chunking strategy for video transcripts + Markdown lessons

4. Hybrid retrieval (dense + sparse) recommendations

5. Reranking strategy

6. Per-user scope enforcement (no cross-tenant leakage)

7. Multilingual retrieval — Arabic + English minimum; Arabic word-error-rate is real

8. Vector store choice review — MongoDB Atlas today; pgvector under evaluation

9. Prompt + eval system

10. Supervisor routing prompts

11. Vertical-agent prompts (Courses, Jobs, Comms)

12. Structured-output validation

13. Regression eval set design + CI integration

14. Failure-mode catalog

15. Cost discipline

16. Per-feature + per-organization token budgets with enforcement (we bill at org level)

17. Cache strategy (we already cache canvas cards by content version)
    Multi-tier model routing — frontier (Sonnet / GPT-4o) for paid cohorts, mid-tier for general learners, cheap-tier or self-hosted for unverified
    Anti-abuse limits — topical-relevance classification, per-user daily caps
    Cost reporting to PostHog dashboard

Our current stack

• LLMs: OpenAI + Anthropic (multi-provider posture)
• Orchestration: LangChain.js + LangGraph (supervisor + sub-agent pattern)
• Vector store: MongoDB Atlas (pgvector swap under evaluation)
• Backend: Node.js, Express, BullMQ workers, MySQL (Aurora)
• Frontend: Next.js 15 App Router, React, Tailwind
• Eval / observability: PostHog (in-flight); LangSmith or Helicone under evaluation

What success looks like
First 3 months we should have:

• Architecture assessment
• Working RAG/retrieval pass with documented quality metrics on a fixture eval set
• Production-ready prompt + eval pipeline in CI
• Adaptive AI framework that will improve based on learners' interactions
• Scaffolding for evaluations / quality control
• Cost projection for ~10K learners with cap + cache + tier strategy locked

Who you are

• Required: - Built production agentic systems before — not just chat wrappers around an LLM API
• Strong production RAG experience — chunking, retrieval quality, eval discipline
• Comfortable in * * * * JavaScript / TypeScript (Node + Next.js) - LangChain.js / LangGraph experience, or strong opinions on alternatives you can defend
• Cost-aware — you've watched LLM bills explode and have systems-level opinions about budgets, caches, multi-tier routing
• Strongly preferred: - Multilingual retrieval (especially Arabic)
• Eval framework experience (LangSmith, Helicone, custom)
• Vector store experience beyond Mongo (pgvector, Qdrant, Pinecone)
• Worked on platforms (not just internal tools) — you've shipped to real users