NEWPosted 1 hour ago

Job ID: JOB_ID_7417

Role Summary:

We are seeking a highly skilled Technical Architect with expertise in Palantir Foundry and Palantir AIP to design and implement cutting-edge data and AI solutions. This role involves architecting end-to-end solutions, leading delivery teams, and engaging with clients to translate business requirements into actionable technical roadmaps. You will be instrumental in leveraging Palantir’s capabilities to solve complex business challenges, particularly in the realm of Generative AI and data engineering.

Key Responsibilities:

  • Solution Design & Architecture: Design end-to-end data and AI solutions on Palantir Foundry, including ontology modeling, pipeline architecture (Python Transforms, Foundry Rules), and Ontology Object design.
  • AI & LLM Integration: Architect LLM-powered workflows using Palantir AIP, including AIP Logic, AIP Automations, and AIP Evals, for use cases such as intelligent document processing, requirement extraction, answer matching, and automated report generation.
  • Integration Strategy: Define integration patterns between Foundry and external systems (e.g., Salesforce, Snowflake, external APIs) with appropriate data governance and access controls.
  • Technical Roadmapping: Translate client business requirements into actionable, phased technical roadmaps aligned with strategic goals.
  • Delivery & Technical Leadership: Oversee data pipeline health, including scheduled ingestion monitoring, schema conflict resolution, and pipeline failure triage across Foundry environments.
  • Development Guidance: Guide development teams on Foundry Rules pipelines (Java-based), compute module development (C#/Docker), and AIP Logic best practices.
  • AI/ML Implementation: Drive technical decisions around file digitization (PDF/Docx to Markdown using VisionLLM), knowledge base construction, and semantic search implementation.
  • Quality Assurance: Ensure quality and reliability of LLM outputs through AIP Evals, implementing LLM-as-a-judge frameworks, consistency metrics, and continuous evaluation loops.
  • Client Engagement: Serve as the primary technical point of contact for client engagements, building strong relationships with business and technical stakeholders.
  • Use Case Identification: Identify and prioritize high-impact Generative AI use cases aligned with client business goals (e.g., RFP automation, lead management, seller support).
  • Workshops & Training: Conduct architecture reviews, technical workshops, and support training sessions for client and partner teams.
  • Collaboration: Collaborate with Palantir forward-deployed engineers and product teams to align platform capabilities and escalation paths.
  • Knowledge Base Development: Build and maintain centralized knowledge bases in Foundry, including Q+A extraction pipelines from service guides and third-party systems (e.g., Salesforce).
  • Search & Scoring: Design scoring and confidence frameworks for LLM-generated outputs, using keyword and embedding-based (semantic) search.
  • Workflow Automation: Implement cover letter generation, metadata extraction, and document export workflows (Word/Docx via compute modules).
  • Responsible AI: Apply responsible AI principles: bias mitigation, output transparency, human-in-the-loop review workflows, and governance guardrails.

Required Qualifications:

  • Technical Skills:
    • Palantir Foundry: Ontology design, Python Transforms, Pipeline Lineage, Schedules, Foundry Rules (Java), Media Sets, Compute Modules.
    • Palantir AIP: AIP Logic, AIP Automations, AIP Evals, LLM integration, embedding search, prompt design.
    • Data Engineering: Data ingestion, transformation pipelines, schema management, Spark-based compute.
    • AI/ML: LLM deployment, RAG (Retrieval-Augmented Generation), semantic search, confidence scoring, evaluation frameworks.
    • Integration: Salesforce, Snowflake, REST APIs, CDO-approved data connection patterns.
    • Cloud & DevOps: Docker/containerization, CI/CD for Foundry repositories, Git-based workflows.
    • Languages: Python (primary), Java (Foundry Rules), C# (compute modules), SQL.
  • Experience:
    • 8-12 years of overall experience in architecture, data engineering, or AI/ML engineering.
    • 3+ years of hands-on experience with Palantir Foundry in a production environment.
    • Proven experience delivering AI-powered products on Palantir AIP, including LLM-based automation workflows.
    • Experience in regulated or data-sensitive industries (Telecom, Finance, Healthcare, Government) preferred.
    • Track record of leading technical workshops, client presentations, and Day-2 support enablement programs.
    • Experience with Salesforce integrations and enterprise data platforms (Snowflake, Databricks) is a plus.

Special Requirements

Employment Type: C2C. Location: ONSITE – Dallas, TX. Keywords: csharp continuous integration continuous deployment artificial intelligence machine learning Texas

Compensation & Location

Salary: $75 – $100 per year (Estimated)

Location: Dallas, TX

Recruiter / Company – Contact Information

Email: sha.vennapusa@w3global.com

Interested in this position?
Apply via Email

Recruiter Notice:
To remove this job posting, please send an email from
sha.vennapusa@w3global.com with the subject:

DELETE_JOB_ID_7417

to delete@join-this.com.