Staff ML Engineer — Agent Memory & Reasoning

Wand AI; Palo Alto (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

Wand AI seeks a Staff Machine Learning Engineer to advance agent memory, reasoning, and memory-driven workflows. You will build systems that manage context, ensure confidentiality, and scale agent capabilities across the organization.

The role emphasizes practical, shipped solutions with access to modern tooling and large-scale data. You will work with memory-focused components and guide the technical roadmap for agent intelligence.

Qualifications

• Shipped production agents or agent-adjacent systems.
• Experience with memory, context engineering, or techniques that make agents reason better without retraining them.
• Applied builder mindset: ship in days/weeks, not semesters.
• Comfort owning ambiguous, senior-level problems on your own.
• Strong software engineering fundamentals.
• Fluent with vector databases and retrieval frameworks.
• Experience with LLM provider APIs and embedding models.

Responsibilities

• Build agent memory systems and the mechanisms that generate, curate, refine, and store contextual data.
• Design memory with confidentiality and scoping to prevent leakage.
• Develop systems that monitor agent behavior and extract reusable best practices at scale.
• Create reusable 'skills' agents can call on for improved reasoning and decision-making.
• Design tests and benchmarks to confirm improvements.
• Contribute to the technical roadmap for memory and reasoning.

Skills

Agent memory

Memory engineering

Software engineering fundamentals

LLM tooling

LangChain

LLM APIs

Agent evaluation tooling

Communication

Education

MS or PhD

Tools

Pinecone

Weaviate

pgvector

LangChain

LlamaIndex

LangGraph

OpenAI API

Anthropic API

Job description

Wand AI seeks a Staff Machine Learning Engineer to advance agent memory, reasoning, and memory-driven workflows. You will build systems that manage context, ensure confidentiality, and scale agent capabilities across the organization.

The role emphasizes practical, shipped solutions with access to modern tooling and large-scale data. You will work with memory-focused components and guide the technical roadmap for agent intelligence.