AI Engineer

Emergence AI is building next-generation agentic AI systems that move beyond code generation to provable task completion, verification, and long-horizon autonomy. Our Platform focuses on automating complex, mission-critical data workflows, from ingestion and transformation through analysis, decisioning, and action.

We work with customers in semiconductors, life sciences, and other data-intensive industries to turn fragmented, high-stakes data into trustworthy, continuously-operating AI Agents.

Bring AI expertise, product intuition, and a builder's mindset to advance the frontier of what agents can accomplish for our customers. You will work across applied research and engineering to solve many open problems in AI, including:

• Designing AI agent workflows and orchestration systems for our platform and solutions
• Designing optimal data representations and modes of interaction between agents and their environments
• Building verification and safety systems that enable autonomous agent execution in high-stakes enterprise environments

Workflow Orchestration & Custom Agent Builder. Build the platform that lets customers define their own investigation workflows from natural language to production-grade multi-step agents. Own the workflow execution engine, state management, error handling, versioning, and sharing capabilities that make custom workflows reliable and reusable.

Verification & Policy Engine. Design and implement the verification system that makes autonomous agent execution safe, policy-as-code frameworks, constraint checking, audit trails, and proof artifacts in an Enterprise systems. Enable agents to move to autonomous direction when verified safe.

Agent Operations & Observability. Build the provenance tracking, drill-down capabilities, and debugging tools that make agent behavior transparent and debuggable from query execution traces to multi-agent coordination visibility. Make non-deterministic AI systems observable and trustworthy.

Evaluation Infrastructure. Build the shared eval tooling and frameworks that let every team across Emergence measure and improve AI quality systematically, eval harnesses, ground truth management, regression detection, A/B testing for agents.

Context Engineering & Agent Infrastructure. Build the platform-level systems for context management, session state, and memory that all of Emergence agent workflows depend on managing what agents see, remember, and pass between steps.

• Drive cutting-edge AI capabilities across multiple layers of the agent platform from workflow orchestration and verification systems to custom workflow builders and agent operations infrastructure.
• Ensure a high craft and quality bar in both AI agent performance and platform reliability, build systems that are fast, correct, and maintainable.
• Collaborate with fellow engineers, designers, product managers, and customers to integrate platform functionality into frontier agentic products and deliver customer value.
• Contribute to platform reliability, code quality, AI evaluation, testing, and maintenance across the broader engineering team.
• Mentor and elevate engineers around you, share knowledge, review code thoughtfully, and raise the technical bar for the team.

• 8+ years of experience building backend systems, distributed systems, or data infrastructure, with at least 2+ years focused on AI/ML engineering in production environments.
• Experience building and shipping multi‑model or multi‑provider AI systems in production using LLM APIs (OpenAI, Anthropic, or similar), prompt engineering, function calling, or agent frameworks at scale.
• Track record at both startups and enterprise companies, you know how to move fast while maintaining reliability and can navigate both worlds effectively.
• Familiarity with context management, session state, or memory systems in AI or distributed systems. You've thought about what the model sees and why it matters.
• Experience with evaluation frameworks, testing strategies for AI systems, or quality measurement in production ML systems.
• Strong systems thinking around safety,…