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.
What You'll Be DoingOwn 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.
What You'll Add to DigitalOceanWe'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
Preferred QualificationsStrong 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.
Compensation Range: *This is a hybrid role
#LI-Hybrid
Application Limit: You may apply to a maximum of 3 positions within any 180-day period. This policy promotes better role-candidate matching and encourages thoughtful applications where your qualifications align most strongly.
