Staff AI Engineer - OpenClaw

Discover International; United States; On-site; USD 180,000 - 240,000; Full time

Job summary

Discover International is seeking a Staff AI Engineer to architect and lead a brand-new Enterprise AI squad. You will be the technical anchor behind a central AI orchestrator and its distributed execution agents, evolving a production platform into a sophisticated multi-agent system for payments, lending, and fraud.

You will own end-to-end infra for AI deployment, drive LLMOps and observability, and define future architectural direction in a high-growth environment.

Qualifications

• 8+ years of hands-on software engineering experience.
• 2+ years building production-grade LLM applications.
• Excellent Python and system architecture expertise.
• Proven experience with complex agentic systems: RAG, tool-calling, vector databases, memory/state management.
• High ownership in an early-stage squad, able to define architecture and ship it.
• Bonus: Open CLAW, Hermes, or similar agent frameworks.

Responsibilities

• Architect and scale the core infrastructure for a central AI orchestrator and its connected execution agents.
• Lead infrastructure-first AI development—from containerization to CI/CD, availability, security, and post-launch stability.
• Build production-grade LLMOps and observability: tracing reasoning paths, tool-calling success rates, and latency bottlenecks.
• Design automated evals-as-code pipelines using LLMs as judges, semantic similarity testing, and adversarial benchmarking.
• Optimize RAG pipelines and agent loops for production: caching, prompt compression, and model routing.
• Set operational best practices for AI deployment and map future team/infrastructure needs.

Skills

Software engineering

LLM applications

Python

System architecture

LLM APIs

Agent frameworks

Ownership

Open CLAW / Hermes

Tools

Docker

Kubernetes

Job description

Agentic AI & LLM Infrastructure | High-Growth (Series B, $100M+ raised)

Our client is a hyper-growth, venture-backed company on a mission to make financial services radically more accessible for underserved communities. Their flagship product is an AI-powered conversational platform used by customers every day to move money — fast, affordable, and as easy as sending a text.

Now they're building their next chapter: a new Enterprise AI squad, and they need a Staff AI Engineer to architect it.

You'll be the technical anchor behind the company's central AI orchestrator and its distributed execution agents - evolving a production conversational AI platform into a sophisticated multi-agent system capable of reasoning, planning, and automating complex workflows across critical functions like payments, lending, and fraud.

This is a foundational hire. You'll shape the architecture of a brand-new squad, define what gets built next, and set the standard for how AI is deployed across the business.

Responsibilities:

• Architect and scale the core infrastructure for a central AI orchestrator and its connected execution agents
• Lead infrastructure-first AI development - owning the full lifecycle from containerization (Docker/Kubernetes) through CI/CD, availability, security, and post-launch stability
• Build production-grade LLMOps and observability: tracing reasoning paths, tool-calling success rates, and latency bottlenecks across complex agentic workflows
• Design automated "evals-as-code" pipelines using LLM-as-a-judge, semantic similarity testing, and adversarial benchmarking
• Optimize RAG pipelines and agent loops for production - caching, prompt compression, and model routing to balance cost and performance
• Set operational best practices for AI deployment and help map out future team and infrastructure needs

Required Skills:

• 8+ years of hands-on software engineering, with a proven background in infrastructure and systems development
• 2+ years building and deploying production-grade LLM applications
• Exceptional Python and deep system architecture expertise; mastery of core LLM APIs and agentic frameworks
• Proven experience with complex agentic systems: RAG, tool-calling, vector databases, and advanced memory/state management
• High ownership and comfort in an early-stage squad - someone who can spot operational bottlenecks, propose the architecture, and ship it
• Bonus: hands-on experimentation with Open CLAW, Hermes, or other advanced open-source agent frameworks

If you thrive at the intersection of deep infrastructure, operational excellence, and agentic AI this is your mission.