AI Agent Architect
Spearbit
Location
United States
Employment Type
Full time
Location Type
Remote
Department
Delivery Operations
About Spearbit & Cantina:
Founded in 2021 by former Ethereum Foundation Solidity engineers, Spearbit tackles Web3 security challenges. Our founding team built the leading blockchain language and secured the largest smart contract, protecting over $160B in value.
We're building Cantina —the "GitHub for Security"—connecting security researchers with projects needing expertise. Our Cantina security platform has powered major competitions and serves the leading projects in Web 3. It currently supports collaborative security reviews, public and private security competitions, bug bounty programs, incident response, and AI code analyzer.
Similar to how cloud-security startups emerged previously, Cantina aims to be the definitive code-security platform for the future.
The Opportunity:
We are looking for an AI Agent Architect for our Operations and Sales teams. You will lead the design, development, deployment, and continuous optimization of AI agents (autonomous or semi-autonomous systems) that support Spearbit’s internal operations and sales workflows. Your impact will be felt across the business — you’ll help automate repetitive tasks, augment decision-making, and enable scaling of high-touch activities.
Responsibilities:
Partner with operations, sales, and cross-functional teams to identify high-leverage opportunities for AI agents (e.g., lead qualification, outreach orchestration, operational monitoring, internal automations).
Architect, build, test, and deploy AI agents (prompt-based agents, agent frameworks, RAG pipelines, multi-agent orchestration).
Integrate agents into internal systems (CRM, workflow tools, internal dashboards, triggers, APIs, etc.).
Monitor agent performance, define metrics (accuracy, throughput, ROI), and continuously iterate.
Establish guardrails, safety checks, fallback logic, and human-in-the-loop mechanisms.
Document designs, agent behaviors, and escalate edge cases/pitfalls.
Train stakeholders and end users on how to interact with and govern these agents.
Stay current on agent frameworks, LLMs, prompt engineering, tool-augmented agents, and automation best practices; evangelize suitable innovations within the team.
Requirements:
Must-have
3+ years experience working with AI systems, especially prompt engineering, agent orchestration, embeddings/RAG, and LLM workflows.
Experience building agents (or autonomous/semi-autonomous software) applied to real business processes (sales, operations, workflow automation).
Strong software engineering skills: Python (or comparable), REST APIs, data pipelines, webhooks, etc.
Familiarity with CRM systems (e.g. HubSpot, Salesforce, Pipedrive), internal workflow tooling (Zapier, n8n, Make, etc.), possibly custom enterprise stacks.
Ability to translate non-technical needs (from ops/sales) into technical spec and vice versa.
Metrics-driven: you think in terms of KPIs, failure modes, monitoring, and ROI.
Excellent communication skills — comfortable working across technical and non-technical teams.
Ownership mindset: you see an opportunity, you dive in, you ship.
Nice-to-have
Prior experience with agent frameworks (AutoGPT, LangChain agents, ReAct, Toolformer, etc.).
Experience with vector stores, embeddings infrastructure, retrieval augmented generation.
Knowledge of security, access controls, audit logging.
Exposure to scaling internal tooling in a startup environment.
Benefits
Competitive salary and performance-based compensation opportunities
Opportunity to work in an early-stage startup with a talented and passionate team.
Exposure to high-profile clients in the blockchain and cryptocurrency industry
Comprehensive health, dental and vision benefits
401k plan with company match
Join Spearbit and help us build the future of code security!