Palantir Data Solution Architect

EPAM Systems; Hyderabad; On-site; INR 3,500,000 - 6,000,000; Full time

Job summary

EPAM Systems is seeking a seasoned Palantir Data Solution Architect to lead design and implementation of enterprise-scale data and AI platforms for Insurance/Reinsurance clients.

The role focuses on Foundry adoption, GenAI solutions, and intelligent chatbot ecosystems to enable automation, decision intelligence, and regulatory-compliant data platforms across end-to-end data lifecycles.

Qualifications

• 13 to 18 years of experience in Data Software Engineering.
• Expertise in Palantir Foundry including Ontology, Pipelines, Workshop, Quiver, Code Repositories, alongside AIP and Apollo.
• Knowledge of GenAI concepts including LLMs, RAG and embeddings.
• Skills in prompt engineering, multi-agent AI architectures and ML flow model lifecycle.
• Proficiency in Data Engineering including Spark, SQL and Databricks.
• Understanding of ETL/ELT design and distributed systems.

Responsibilities

• Design and deploy data pipelines, Ontology models and data workflows in Foundry.
• Enable end-to-end data lifecycle management from ingestion through transformation to consumption.
• Implement data lineage, governance and auditability aligned with BFSI compliance.
• Architect AI applications using Palantir AIP, including agents for underwriting, claims and risk analysis.
• Build RAG-based solutions integrating structured and unstructured BFSI data.
• Integrate external LLMs such as Azure OpenAI and GPT securely within enterprise systems.
• Design domain-aware chatbots, assistants and orchestration interfaces for claims processing and regulatory insights.
• Lead end-to-end solution architecture and platform design, define best practices and accelerators.
• Mentor engineering teams and drive architecture governance.

Skills

Palantir Foundry

GenAI concepts

Prompt engineering

ML lifecycle

Spark

Databricks

Python

SQL

Scala/Java

Distributed systems

Tools

Palantir Foundry

LangChain

AIP

Delta Lake

Spark

Databricks

Azure OpenAI

GPT

APIs

Job description

We are looking for a seasoned Palantir Data Solution Architect to lead the design and implementation of enterprise-scale data and AI platforms for Insurance/Reinsurance clients. This role will drive Foundry adoption, AIP-powered GenAI solutions, and intelligent chatbot ecosystems to enable automation, decision intelligence, and regulatory-compliant data platforms.

Responsibilities

• Design and deploy data pipelines, Ontology models and data workflows in Foundry
• Enable end-to-end data lifecycle management from ingestion through transformation to consumption
• Implement data lineage, governance and auditability aligned with BFSI compliance
• Architect AI applications using Palantir AIP, including agents for underwriting, claims and risk analysis as well as intelligent decision-support systems
• Build RAG-based solutions integrating structured and unstructured BFSI data
• Integrate external LLMs such as Azure OpenAI and GPT securely within enterprise systems
• Design domain-aware chatbots, assistants and orchestration interfaces for claims processing, policy servicing and regulatory insights
• Leverage LangChain/LangGraph and AIP for multi-agent workflows and contextual responsesBuild scalable pipelines using Spark, Databricks and Delta Lake across batch and real-time architectures
• Integrate Foundry with core BFSI systems including Policy Admin, CRM, Risk and Finance
• Lead end-to-end solution architecture and platform design, define best practices, reusable frameworks and accelerators
• Mentor engineering teams and drive architecture governance
• Ensure adherence to BFSI regulations including GDPR and PII audit controls, and implement role-based access control, data security and monitoring

Requirements

• 13 to 18 years of experience in Data Software Engineering
• Expertise in Palantir Foundry including Ontology, Pipelines, Workshop, Quiver, Code Repositories, alongside AIP and Apollo
• Knowledge of GenAI concepts including LLMs, RAG and embeddings
• Skills in prompt engineering, multi-agent AI architectures and ML flow model lifecycle
• Proficiency in Data Engineering including Spark, SQL and Databricks
• Competency in ETL/ELT design
• Proficiency in Python, with SQL and Scala/Java preferred
• Understanding of distributed systems, cloud platforms and API-driven design
• Strong communication and stakeholder management skills with the ability to drive technical discussions
• Analytical, problem-solving mindset that is autonomous, detail-oriented and collaborative

Nice to have

• Background in Insurance/Reinsurance domain covering Claims, Underwriting and Premium
• Familiarity with Policy, Treaty data and related domain expertise