About the role

Aplyr's Quick Take

This role is for a Lead/Staff Engineer focused on building a sophisticated AI Agent platform. You'll be working on creating an infrastructure that supports complex reasoning and task execution, rather than just simple chat interfaces. It's an individual contributor role with a strong emphasis on technical problem-solving and system design.

Good fit

Ideal candidates will have extensive experience in software engineering, particularly in AI and systems architecture. A passion for tackling complex challenges and a hands-on approach to building robust solutions will help you thrive here.

Worth noting

The role emphasizes developing a unique Agent architecture for high-stakes applications, which may appeal to those looking for impactful work. However, the spec is vague on day-to-day responsibilities, so be prepared for some ambiguity.

We are building the next-generation Agent Brain.

This isn't just another "wrapper around LLM APIs with a chat UI." It is a purpose-built Agent architecture designed for complex knowledge work. Our target scenarios focus on high-value domains like IP and R&D: these involve long-chain tasks, heterogeneous data sources, and strict evidence requirements, ultimately demanding verifiable outcomes rather than just conversational outputs.

You will be building a reusable Agent infrastructure and a reasoning/orchestration kernel. Your core focus will be solving three major challenges:

How the Agent Runs — Execution Engine: The mechanics of the agent loop. This includes multi-step reasoning cycles, middleware pipelines, Planning & SubAgent orchestration, Checkpointing & state recovery, and execution controls (Permissions / Cost / Clarification).
How the Model Thinks per Turn — Context Engineering: It’s not about stuffing the context window; it’s about organizing attention. You will solve core issues such as: input standardization, determining the exact capabilities and states exposed per turn, compressing long histories into an effective working memory, structured degradation under budget constraints, and normalizing tool outputs into traceable evidence.
What the Agent Can Use — Capability Foundation: Sandbox environments (Docker / K8s), Memory Store, MCP Hub, Skills Engine, File System & Upload Pipelines, multi-tenant isolation, security, and observability.

If you have a long-term passion for transforming raw model capabilities into robust systems capable of reliably executing complex tasks, this role is a perfect match.

Skills & Tags

docker ai ios data design

Aplyr's read

PatSnap is a dynamic innovation intelligence platform attracting professionals passionate about intellectual property, R&D, and technology trends to drive business innovation.
Synthesized from recent postings & public sources

What's promising

•PatSnap offers a unique platform that integrates patent data with R&D insights.
•The company is at the forefront of innovation intelligence, leveraging AI to enhance analytics.
•PatSnap's focus on technology trends helps businesses stay competitive in rapidly evolving markets.

What to watch

•High competition in the innovation intelligence sector may impact market share.
•Rapid technological changes require constant adaptation and can strain resources.
•Limited public information about employee satisfaction and company culture.

Why PatSnap

•PatSnap combines patent analytics with R&D insights, setting it apart from competitors.
•The platform's AI-driven approach provides deeper, actionable insights for businesses.
•PatSnap's specialization in life sciences and semiconductors addresses niche industry needs.

Aplyr’s read is generated by AI from public sources. Was it useful?

About PatSnap

PatSnap

patsnap.com

View company

PatSnap is a leading innovation intelligence platform that provides insights and analytics on patents, R&D, and technology trends to help businesses drive innovation.