Applied Research

Building AI agents that can remember a conversation is the easy part. Building agents that maintain useful accurate and trustworthy memory across long-running workflows is one of the hardest open problems in production AI today.

That’s what this team works on. As a Staff AI/ML Engineer on our Applied Research team you’ll own the technical direction for agent memory in DigitalOcean’s agentic systems: how agents store context retrieve relevant information update beliefs personalize experiences and reason over past interactions.

This is a senior IC role with broad technical scope. You’ll set direction run experiments at scale and work cross-functionally with product managers scientists applied researchers engineers and designers to move memory research from prototype to shipped product capability.

Own the agent memory roadmap

• Define and execute the applied research agenda for memory-enabled agentic AI including long-term context retrieval personalization and state management.
• Translate user needs product signals and research findings into practical memory architectures that improve real-world workflows.
• Stay close to the research frontier on agent memory retrieval systems multimodal recall belief revision and long-running agents.

Build production memory systems

• Design and build memory architectures for agentic AI including episodic memory semantic memory user context and long-term recall.
• Build reliable systems that support memory decay fact grounding belief updates context compaction and retrieval across sessions.
• Develop evaluation frameworks that measure memory quality groundedness reasoning reliability personalization quality and user outcomes.

Provide technical leadership

• Set technical direction across architecture modeling decisions experimentation strategy and production readiness — without requiring direct management authority.
• Partner closely with product engineering design science and research teams to move work from ambiguous research ideas to shipped capabilities.
• Communicate complex AI systems clearly to both technical and non-technical stakeholders.

We’re looking for engineers who have shipped real AI systems — not just prototyped them. You likely bring:

• 8+ years of experience building production AI/ML systems LLM-powered products agentic workflows retrieval systems personalization systems or applied research systems at scale.
• Hands-on experience with memory and retrieval systems such as embeddings semantic search knowledge graphs RAG personalization or long-term user context.
• Strong understanding of agentic AI: memory planning tool use state management instruction following self-correction and action execution.
• Strong software engineering in Python and at least one production systems language.
• The judgment to balance research quality product impact latency reliability cost and maintainability — and communicate those tradeoffs clearly

Strong signal

• Experience building memory retrieval personalization or long-context systems in production.
• Experience with agent evaluation offline/online experiments feedback loops or user outcome measurement.
• Prior Staff Senior Staff Tech Lead or equivalent senior IC experience.

Nice to have

• Master’s or PhD in CS ML AI or a related field — or equivalent depth demonstrated through industry work.
• Experience with production ML infrastructure: model serving observability data pipelines feature stores or experimentation platforms.
• Research contributions via peer-reviewed publications patents open-source work or demonstrated applied research impact in AI agents memory systems retrieval personalization or applied ML.

• $216800 - $271000

*This is a hybrid role

JR: 2026-7946

#LI-Hybrid

What We Do

DigitalOcean is the Inference Cloud — a full-stack production-ready cloud platform built to run AI applications with predictable performance sustainable economics and radically simpler operations at scale. We are built for teams turning AI into real products — not just training models. Our advantage is not fewer features but fewer failure modes when operating AI at scale — combining minimal operational overhead predictable cost efficiency and a full-stack cloud that works as a system. Hyperscalers are broad by design. Neoclouds are infrastructure-first. DigitalOcean is inference-first — with a real cloud underneath. It combines inference-optimized compute managed inference software and integrated cloud capabilities that reduce operational burden for teams running real workloads. Inference is the foundation—not the boundary. Everything else builds on top of it.

Why Work With Us

At DO we do career-defining work. We innovate with AI and build cutting-edge tech. Our rewards to match that intensity - to motivate you recognize your impact and give you what you need to thrive. If you have a growth mindset like to think big and bold and are energized by the fast-paced environment you'll find your place here.

Gallery