Agentic AI & Palantir Engineer / Consultant

Agentic AI & Palantir Engineer / Consultant

Remote Or Hybrid for 2-3days a week

Long Term Consulting Company

Local to NJ/NY

Position Overview

We are seeking experienced Agentic AI Engineers / Consultants to support the rapid design, development, and deployment of enterprise AI solutions. Candidates should bring strong hands-on experience across the end-to-end Agentic AI lifecycle, from use-case ideation and experimentation through development, testing, production deployment, and ongoing enhancement.

The engagement will operate in a fast-paced, pod-based delivery environment, requiring individuals who can quickly translate business needs into working AI capabilities and collaborate effectively across business, data, AI, and engineering teams.

Experience with Palantir Foundry and Palantir AIP is heavily preferred. While Palantir expertise is not required for every team member, candidates with deep Palantir capabilities will play an important role in solution delivery and in upskilling other members of their pod.

Key Responsibilities

Agentic AI Development

• Design, build, test, and deploy Agentic AI solutions addressing enterprise business use cases.
• Participate across the complete AI solution lifecycle, including ideation, experimentation, prototyping, development, testing, deployment, and production support.
• Build reusable agentic skills, tools, and capabilities that can be composed across multiple agents and business use cases.
• Design agent workflows involving reasoning, orchestration, tool use, enterprise data, APIs, and human-in-the-loop interactions.
• Rapidly prototype new AI capabilities and transition successful experiments into scalable, production-ready solutions.
• Develop appropriate testing, evaluation, monitoring, and governance approaches for production Agentic AI applications.

Palantir Foundry & AIP

• Develop data and AI solutions using Palantir Foundry and Palantir AIP.
• Build and manage Foundry data pipelines, ontology components, and application capabilities.
• Design enterprise semantic and context layers using Palantir's ontology capabilities.
• Develop AI and LLM-powered workflows using AIP Logic, AIP Automate, and AIP Assist.
• Deploy and operationalize solutions within the Palantir environment.
• Where applicable, serve as a Palantir subject matter resource within the delivery pod and help coach and upskill other team members.

Relevant Palantir experience may include:

• Ontology Manager (OMA)
• Object Types and Link Types
• Action Types
• Interfaces and Property Sets
• Object Explorer
• Data Lineage
• CBAC attribute sets
• Ontology Linter
• Foundry Marketplace
• AIP Logic
• AIP Automate
• AIP Assist

Additional Technical Responsibilities

Depending on role and experience level, candidates may also:

• Develop Agentic AI solutions using Azure AI Foundry, Databricks, and related cloud AI services.
• Work with Databricks Genie and other emerging agentic and conversational data capabilities.
• Build and maintain Git repositories, branching strategies, automated testing, and CI/CD pipelines supporting production AI deployments.
• Engineer and integrate structured and unstructured enterprise data for AI applications.
• Design semantic layers, enterprise ontologies, knowledge/context layers, or context spines that provide agents with reliable business context.
• Integrate enterprise systems, APIs, databases, vector stores, search capabilities, and other tools with AI agents.
• Work with models from OpenAI, Anthropic, and other leading LLM providers.
• Evaluate models based on quality, latency, security, scalability, deployment architecture, and cost.
• Implement appropriate approaches for LLM evaluation, observability, guardrails, security, and cost optimization.

Required Qualifications

• Strong hands-on experience developing Agentic AI or advanced Generative AI applications.
• Demonstrated experience across multiple stages of the AI lifecycle, including:
• Ideation and experimentation
• Solution architecture and development
• Testing and evaluation
• Production deployment
• Monitoring and continuous improvement
• Experience creating reusable AI agent capabilities, skills, tools, or components that can support multiple business use cases.
• Strong software engineering and problem-solving capabilities.
• Experience integrating AI applications with enterprise data sources, APIs, and business systems.
• Ability to work effectively in a rapid development and deployment environment with evolving requirements.
• Strong collaboration and communication skills, including the ability to work with technical and business stakeholders.

Highly Preferred Qualifications

• Hands-on experience with Palantir Foundry and/or Palantir AIP.
• Experience designing and implementing Palantir Ontologies.
• Experience with AIP Logic, AIP Automate, and AIP Assist.
• Experience deploying production applications or AI solutions within the Palantir platform.
• Experience with Azure, Azure AI Foundry, Databricks, and/or Databricks Genie.
• Experience implementing automated CI/CD pipelines using GitHub and DevOps tooling.
• Strong data engineering experience across structured and unstructured datasets.
• Experience building semantic layers, ontologies, knowledge graphs, or enterprise context layers, ideally within Azure, AWS, GCP, Palantir, or Databricks environments.
• Experience deploying and operating models from OpenAI, Anthropic, and other major LLM providers.
• Understanding of LLM model selection, performance evaluation, deployment patterns, security, and token/inference cost optimization.

Ideal Candidate Profile

The ideal candidate combines hands-on Agentic AI engineering expertise with strong enterprise data and software engineering fundamentals. They are comfortable moving quickly from an ambiguous business problem to a prototype and then hardening that prototype into a production solution.

Candidates with Palantir experience should be capable not only of building within the platform but also of helping other engineers become productive with Foundry, AIP, and Palantir's ontology-driven development model.

Success in this role requires a practical, delivery-oriented mindset, strong technical judgment, and the ability to operate effectively in multidisciplinary teams working at the pace required for rapid AI experimentation and production deployment.