Senior Applied AI Engineer

🔥 14 hours ago

🇺🇸 United States – Remote

⏰ Full Time

🟠 Senior

🤖 AI Engineer

👻 Ghost score 10%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Foresite Cybersecurity

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2013

💼 Consulting

🔒 Cybersecurity

☁️ SaaS

💰 Venture Round - Foresite on 2019-01

Consulting • Cybersecurity • SaaS

Foresite Cybersecurity is a managed security services and SecOps company founded in 2013 that helps organizations of all sizes defend against modern cyber threats. It combines human cybersecurity expertise, a proprietary security and compliance management platform (ProVision), and partnerships with cloud providers (notably Google Cloud) and AI technologies to deliver monitoring, incident response, compliance, and security automation as a service. Foresite positions itself as a B2B partner and extension of clients' security teams, serving thousands of customers with managed detection and response, SOC services, and security engineering.

📋 Description

• Architect, harness, and deploy production-grade autonomous agent networks using ADK, A2A communication, and agentic frameworks • Automate multi-step security triage and investigation workflows • Own model selection, prompt engineering/harnessing, context retrieval and RAG pipelines, agent orchestration, and automated evaluation/observability • Manage context windows and optimize token budgets • Implement prompt caching and pruning • Minimize latency across real-time RAG, function-calling, and multi-agent interaction loops • Collaborate with engineering teams to embed agentic capabilities into customer- and analyst-facing web applications • Design secure AI architectures enforcing customer data isolation, zero-leakage context management, and enterprise-grade privacy controls • Establish standards for LLM development and agent evaluation pipelines • Elevate AI engineering practices across the organization • Own AI/LLM solutions from concept and prototyping through production rollout, monitoring, and iteration • Design scalable data access patterns and modular service/repository architectures • Build and deploy AI and agentic automation protecting global enterprises from cyber threats • Partner with product managers and security analysts to deliver operationally valuable features

🎯 Requirements

• 5+ years of software engineering experience • Production coding experience, not just notebooks • Deep practical experience using Agent Development Kit (ADK) • Proven experience integrating LLMs into production environments • Experience with prompt engineering/harnessing, context management, RAG architectures, agent frameworks, evaluation, and observability • Deep proficiency in React 18/19 and TypeScript • Comfort with React Router v7 and modern routing patterns • Experience designing schemas and writing queries across PostgreSQL and Firestore • Familiarity with modern ORMs and runtime validation • Experience designing secure multi-tenant AI architectures with strict customer data isolation • Strong understanding of scalable, highly available cloud-native system design • Experience working closely with product teams to ship user-facing features • Proven ownership of AI/LLM solutions from concept and prototyping through rollout, monitoring, and iteration in production • Hands-on experience deploying modern LLMs, agent frameworks, ADKs, or A2A protocols to production • Proficiency balancing performance, token usage, context-window constraints, and latency in RAG or multi-agent architectures • High proficiency writing production code, designing database schemas, and reasoning about performance across React 18/19, TypeScript, PostgreSQL, and Firestore • Experience with secure multi-tenant AI systems requiring customer data separation and compliance-boundary enforcement • Practical experience with prompt harnessing, multi-agent orchestration, function calling/tool use, evaluation frameworks, and LLM observability • Experience in cloud-native AI environments; Vertex AI/GCP preferred, AWS/Azure also welcome • Familiarity with Claude, Gemini, GPT-4, Llama, and Mistral • Data engineering competency across relational and document databases • Ability and interest to partner with product managers and security analysts • Nice to have: Terraform or similar IaC tools • Nice to have: cloud security tools such as Google Cloud SecOps, Security Command Center, Mandiant, or SOAR systems • Nice to have: multi-modal workflows, streaming agent architectures, or custom agent routing engines

🏖️ Benefits

• Pre-approved vendor and technical training entirely at the employer's expense • Supportive peer code reviews and deep technical mentorship • Robust medical coverage • Company-paid dental plan • Short-term disability (STD) plan • Long-term disability (LTD) plan • Paid vacation starting at 3 weeks, accruing up to 4 weeks based on tenure • Paid sick leave • 10 paid company holidays, including a floating holiday • 401(k) company match: 100% of the first 3% contributed and 50% of the next 2% • Modern tech stack and best practices • Developer well-being prioritized