Architect Dynamic Memory Management for LLM/agent apps (ingestion, CRUD, retrieval)
Design RAG/memory architectures with vector DBs, relational stores, knowledge graphs
Develop multi-stage retrieval and ranking (re-ranking, salience, deduplication)
Build end-to-end pipelines for retrieval-augmented context and memory selection
Train and post-train models for reliable tool calling (tool selection, schemas, planning)
Establish evaluation frameworks across offline/online metrics (memory accuracy, latency)

🎯 Requirements

Shipping LLM-powered agents to production with measurable impact
Deep expertise in retrieval and ranking for RAG and memory apps
Design memory behaviors: summarization, consolidation, forgetting, personalization
Improve structured tool calling via post-training and safety gates
Adaptive AI fluency; accelerate experiments, code, and evaluation

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot