An application made for this job — a tailored resume and cover letter that speak straight to the posting.
Foresite is seeking a Senior Applied AI Engineer to shape how state-of-the-art AI and autonomous agents power our MSSP platform. We are building the next generation of AI-driven security operations, transforming threat detection, investigation, and response.
You will own model selection, RAG pipelines, latency optimization, and mentorship across the team, applying best practices for privacy and secure architectures within a GCP-centric environment.
Foresite is looking for a Senior Applied AI Engineer to shape how state-of-the-art AI and autonomous agents power our Managed Security Services Provider (MSSP) platform. We are building the next generation of AI-driven security operations, transforming how threat detection, investigation, and response are conducted.
In this role, you will move beyond basic API integrations to build and deploy complex, multi-agent AI systems. You will leverage the latest model architectures, agent harnesses, Agent Development Kits (ADK), Agent-to-Agent (A2A) interaction patterns, and emerging frameworks. While our ecosystem is anchored on Google Cloud Platform (GCP), we value deep hands-on expertise across model ecosystems (OpenAI, Claude, Gemini, Llama, Mistral) and cloud environments.
Build Complex Agentic Workflows: Architect, harness, and deploy production-grade autonomous agent networks using ADK, A2A communication, and state-of-the-art agentic frameworks to automate multi-step security triage and investigation workflows.
End-to-End AI Architecture: Own model selection, prompt engineering/harnessing, context retrieval (RAG pipelines), agent orchestration topologies, and automated evaluation/observability frameworks.
Production Optimization: Manage context windows, optimize token budgets, implement prompt caching/pruning, and aggressively minimize latency across real-time RAG, function calling and other such multi-agent interaction loops.
Full-Stack Integration: Collaborate with engineering teams to embed agentic capabilities directly into our customer- and analyst-facing web applications built on React 18/19, TypeScript, PostgreSQL, and Firestore.
Secure Multi-Tenancy: Design secure AI architectures enforcing strict customer data isolation, zero-leakage context management, and enterprise-grade privacy controls.
Technical Leadership & Mentorship: Establish standards for building with LLMs, agent evaluation pipelines, and elevate AI engineering practices across the organization.
Engineering Principles: 5+ years of software engineering experience with strong fundamentals (you write production code, not just notebooks).
AI/LLM Integration: Deep, practical experience using Agent Development Kit. You should have a proven track record of integrating LLMs into