
cognee builds an OSS knowledge engine for AI apps and AI agents. cognee turns scattered data into a self-improving memory graph. Our ECL pipeline (Extract, Cognify, Load) ingests data from 38+ sources, structures it into a knowledge graph with embeddings and relationships, and makes it searchable. The memify layer then refines this graph through feedback loops: rated responses feed back into edge weights, so the memory gets sharper with use. Cognee unifies three storage layers (relational, vector, and graph) into a single engine. It plugs into the tools teams already use: Claude Agent SDK, OpenAI Agents SDK, LangGraph, Google ADK, n8n, Amazon Neptune, Neo4j, and more. policy: https://topoteretes.notion.site/Privacy-Policy-11237007fa82807e8fced55da84276f7

cognee builds an OSS knowledge engine for AI apps and AI agents. cognee turns scattered data into a self-improving memory graph. Our ECL pipeline (Extract, Cognify, Load) ingests data from 38+ sources, structures it into a knowledge graph with embeddings and relationships, and makes it searchable. The memify layer then refines this graph through feedback loops: rated responses feed back into edge weights, so the memory gets sharper with use. Cognee unifies three storage layers (relational, vector, and graph) into a single engine. It plugs into the tools teams already use: Claude Agent SDK, OpenAI Agents SDK, LangGraph, Google ADK, n8n, Amazon Neptune, Neo4j, and more. policy: https://topoteretes.notion.site/Privacy-Policy-11237007fa82807e8fced55da84276f7
What they do: Open-source knowledge-graph + vector store platform that creates memory for AI apps and agents
Founded / HQ: Founded 2024; Berlin, Germany
Product options: Self-hosted and managed Cognee Cloud with API and integrations
Recent funding: $1.5M announced (Nov 2024); homepage banner states $7.5M seed led by Pebblebed
Memory and knowledge management for AI applications and agents; data unification and semantic search.
2024
Artificial intelligence / developer platform
$1.5M (company blog announcement)
Company homepage also displays a banner stating a $7.5M seed led by Pebblebed; third-party profiles list multiple investors.
“Backed by early-stage investors including 42CAP and a named group of angel/VC backers”
| Company |
|---|
Cognee is building the memory engine + data plane for AI agents to plan, reason, and act. Our open-source Python SDK is in production at 70+ companies, hit GitHub Trending, and runs 550,000+ times per month. We've won early customers (including top-10 Pharma) and recently raised a large Seed.
We are looking for a Principal Engineer / Lead for the Python SDK to own the technical vision, architecture, and execution of Cognee's primary developer interface. This role is critical: the Python SDK is the product for most users. You will set the standard for SDK quality, ergonomics, performance, and long-term maintainability, while working closely with platform, infra, and product teams to ensure Cognee feels world-class for developers.
What You Will Build SDK Architecture & Technical Vision Define and own the long-term architecture of the Cognee Python SDK, ensuring clarity, extensibility, and stability as usage scales.
Developer Experience at Scale Design APIs that feel intuitive, composable, and hard to misuse—serving both early-stage startups and large enterprises.
Performance & Reliability Optimize SDK performance for high-throughput workloads, large memory graphs, and production AI agent systems.
API & Abstraction Design Decide what belongs in the SDK vs the platform. Build clean abstractions over complex systems (vector stores, graphs, memory lifecycle).
Open-Source Leadership Act as the technical steward of the open-source SDK: reviews, RFCs, contribution guidelines, and community standards.
Cross-Team Technical Leadership Work closely with platform, infra, and DevRel to ensure the SDK cleanly integrates with control plane, databases, and deployment models.
Quality & Engineering Excellence Establish best practices around testing, versioning, backwards compatibility, documentation, and release processes.
Requirements Principal-Level Engineering Experience 8+ years of software engineering experience, with clear ownership of critical systems or developer-facing platforms.
Deep Python Expertise Mastery of Python, including async patterns, packaging, typing, performance optimization, and SDK design best practices.
SDK / API Design Track Record Proven experience building and maintaining widely-used SDKs, libraries, or developer platforms.
Distributed Systems Understanding Strong intuition for how SDKs interact with distributed backends, databases, and cloud infrastructure.
AI / Data Systems Familiarity Experience with LLMs, vector databases, graph systems, or data-intensive applications. Technical Leadership Comfortable making high-impact architectural decisions and mentoring senior engineers without heavy management overhead.
Open-Source Experience Prior experience maintaining or leading open-source projects used by external developers. Nice to Have Experience with agent frameworks, vector search, or graph databases Background in developer tools, infra, or platform engineering
Strong opinions about API ergonomics and DX (and the ability to defend them) Experience scaling open-source projects with large external contributor bases
Benefits Top-of-market compensation + meaningful equity
Ownership over a core, business-critical product surface
Direct access to founders and real influence on product direction High autonomy, low bureaucracy, high trust
Opportunity to define the de facto memory SDK for AI agents