GenAI Application Engineer

Capgemini•New York, NY

3d•Onsite

About The Position

As a GenAI Application Engineer, you will design, develop, and deploy intelligent applications leveraging advanced LLMs and generative AI technologies. You will deliver end‑to‑end solutions, implement RAG architectures, integrate diverse data sources, and build high‑quality prototypes for next‑generation Advisor Assistance tools.

Requirements

Expertise in Python
LLMs exposure to Open AI or Anthropic
Agentic framework like Lang Chain or Lang graph
Develop RAG pipelines embeddings vector search and knowledge integrations

Nice To Haves

CICD
containers
LangChain
Semantic Kernel

Responsibilities

Build and integrate applications using LLMs multimodal models and GenAI frameworks
Develop RAG pipelines embeddings vector search and knowledge integrations
Develop AI automation intelligent tooling and AIassisted engineering practices
Build production ready prototypes that enhance and streamline workflows
Develop RAG Architectures Knowledge Systems
Integrate structured and unstructured content from internal and external systems
Optimize retrieval performance latency relevance and RAG evaluation metrics
Gather and consolidate data from diverse sources such as REST APIs databases enterprise systems and document repositories
Implement system prompts agent architectures multimodal workflows and AI orchestrated tools
Prototype conversational interfaces advisor systems and AI assistants
Develop intelligent tooling agents and automation to augment engineering workflows
Embed Gen AI features into existing processes to enhance productivity and decision making
Design and deliver production ready prototypes and proofs of concept demonstrating feasibility and business value
Iterate quickly based on user and stakeholder feedback
Package and deploy applications using containers APIs and CICD pipelines
Apply monitoring observability testing and secure coding practices
Ensure compliance with Responsible AI privacy and data governance standards