We are seeking a highly skilled Agentic AI Engineer to design, build, and deploy next-generation AI Agents within Palantir’s Artificial Intelligence Platform (AIP). In this role, you will develop autonomous, decision-support, and workflow-driving AI systems that augment human operators, automate mission-critical processes, and unlock new value for enterprises and government partners.
You will work at the intersection of machine learning, reasoning systems, and Palantir’s ontology-driven architecture, translating complex data ecosystems into intelligent, actionable AI agents that operate securely and responsibly.
AI Agent Development: Design, prototype, and productionize agentic AI systems within Palantir AIP, leveraging LLMs, multi-agent orchestration frameworks, and Palantir’s ontology.
Workflow Automation: Build intelligent agents that can plan, reason, and execute multi-step tasks across enterprise workflows (e.g., supply chain optimization, financial decision-making, operational command-and-control).
Integration & Orchestration: Connect agentic AI capabilities to Palantir Foundry, Gotham, and AIP pipelines, ensuring seamless interoperability with customer data and applications.
Safety & Governance: Implement robust guardrails, monitoring, and human-in-the-loop mechanisms to ensure AI agents act responsibly, transparently, and within defined policies.
Collaboration: Partner with product managers, forward-deployed engineers, and customer teams to design AI agents aligned with business and mission outcomes.
Innovation: Stay at the forefront of advancements in agentic AI, LLM tool use, reasoning engines, and planning algorithms—bringing cutting-edge approaches into real-world deployments.
Required:
Strong experience with AI/ML, particularly LLM-based systems and agentic frameworks (e.g., LangChain, AutoGen, semantic planners).
Proficiency in Python, with experience integrating AI models into production environments.
Familiarity with Palantir AIP (or strong ability to quickly learn Palantir’s ontology and pipeline-driven architecture).
Understanding of secure, enterprise-grade AI deployment requirements (access control, auditability, compliance).
Background in data engineering, distributed systems, or large-scale analytics platforms.
Preferred:
Experience deploying AI solutions on Palantir Foundry/Gotham/AIP.
Knowledge of reinforcement learning, reasoning algorithms, or multi-agent collaboration methods.
Previous work in regulated industries (finance, defense, healthcare, energy, etc.) where trust and governance in AI are critical.
Ability to design user-facing AI applications and interfaces that drive adoption.