Summary
β¨ AIβGenerated
An AI engineering role focused on building production-grade agentic systems and LLM-powered applications. Responsibilities include developing intelligent workflows, retrieval pipelines, and scalable AI infrastructure.
Highlights
Build advanced AI systems using modern engineering approaches. Work on production-scale AI agents, retrieval systems, and evaluation frameworks.
Description
AI Engineer (Agentic AI) | TypeScript + Vercel AI SDK
π° $130,000 - $180,000 + Super + Bonus
π Sydney CBD | Hybrid, 3 days in office
Junior- Senior Level Positions Available
Their AI team builds agentic systems and LLM-powered products at genuine scale.
This isn't a chatbot wrapper.
Real production agents, real evaluation rigour, real Azure infrastructure underneath.
I'm hiring across levels for this one, junior through senior, so if agentic AI is your thing, worth a conversation regardless of where you're currently sitting.
What you'll be doing:
- Building and extending an agent harness in TypeScript, the runtime loop, tool dispatch, retries, tool-call repair, state persistence
- Designing context and memory strategies for long-horizon agent work, compaction, caching, token budgeting
- Architecting multi-agent and sub-agent systems, lead/worker patterns, delegation, shared state
- Engineering RAG pipelines on PostgreSQL with pgvector, hybrid and re-ranked retrieval
- Building evaluation harnesses and trajectory-level assessment so quality is proven, not just demoed
π Tech:
- TypeScript / Node.js, Vercel AI SDK
- LiteLLM-based model gateway, multi-provider routing
- PostgreSQL + pgvector
- Azure cloud
- Langfuse / OpenTelemetry for observability
What we're looking for:
- Strong TypeScript, confident with the type system for tool schemas and structured outputs
- Hands-on experience building agents with a modern framework, Vercel AI SDK strongly preferred
- Practical context engineering, prompt/response caching, cost and latency trade-offs
- An evaluation-first mindset, you want evidence something works, not just that it demos well
- Senior candidates should also bring multi-agent architecture experience and be comfortable mentoring junior engineers
Why this role stands out:
- β
Genuinely evaluation-led team, not hype-driven
- β
Hybrid, 3 days in a Sydney CBD office
- β
Banded across junior to senior, real progression path in a team that's scaling
- β
Backed by one of the largest professional services firms globally
If you're deep in agentic AI, TypeScript-first, and want to build this stuff at scale rather than just talk about it, this one's worth a confidential chat.
Please apply below or reach out directly to me for more information / a confidential discussion