Software Engineer III, Applied Agentic AI
Proofpoint4 days ago
Remote, Argentina or Córdoba, ArgentinaSenior
Responsibilities
- Build end-to-end reference agentic applications on Proofpoint’s platform.
- Establish best practices for tool design, MCP integration, prompt and context management, memory, planning, cost and latency optimization, failure recovery, and release readiness.
- Design evaluation harnesses with task suites, baselines, and quality, cost, and latency metrics.
- Prototype ambiguous ideas quickly, present findings, and recommend whether approaches should be adopted or abandoned.
- Harden successful prototypes into reusable platform capabilities for product teams.
- Partner with engineers, security researchers, and product technology leads on platform systems.
- Share agentic patterns through demos, design reviews, written guides, and pairing sessions.
- Participate in stakeholder discussions and cross-team technical design.
Requirements
- Bachelor’s or Master’s degree in Computer Science or a related field, or equivalent practical experience.
- At least 3 years of engineering experience, including recent hands-on work with LLM or agentic systems beyond the prototype stage.
- Understanding of agent runtimes, tool and MCP integration, prompt and context management, memory, planning, orchestration, evaluations, tracing, guardrails, rollout, and rollback.
- Strong Python skills; TypeScript and Node.js are a plus.
- Experience working with globally distributed teams.
- Experience building and operating services in a cloud microservices environment with containers and automated deployment; AWS is a plus.
- Ability to diagnose distributed systems using traces and metrics; OpenTelemetry experience is a plus.
- Experience or enthusiasm for agent frameworks and LLM SDKs such as LangGraph, Anthropic Agents SDK, OpenAI Agents SDK, MCP, or LangChain.
- Preferred experience building evaluation harnesses, benchmarks, or ground-truth datasets.
- Preferred experience producing developer-facing reference implementations, SDK samples, or internal enablement material.
- Preferred experience with AG and semantic retrieval, vector stores, hybrid search, and hosted and open-weight models.
- Preferred familiarity with AI coding tools such as Claude Code or Codex and agent interoperability protocols such as MCP and A2A.
Benefits
- Competitive compensation and comprehensive benefits.
- Flexible work environment.
- Annual wellness and community outreach days.
- Recognition for contributions.
- Global collaboration and networking opportunities.
Tech Stack
Categories
About Proofpoint
Proofpoint builds cloud-based cybersecurity and compliance products that protect email, collaboration tools, and sensitive data for enterprises and public-sector organizations. Its portfolio includes email threat protection, data loss prevention, security awareness training, archiving/governance, and safeguards for SaaS and AI-driven workflows, sold as subscription software and services. Founded in 2002 and headquartered in Sunnyvale, it is owned by Thoma Bravo, and reports that over 80 of the Fortune 100 use its products.