GenAI Developer: LLMs, RAG, MLOps & Cloud

Cognizant; Saint Francis (AR); Presencial; USD 80.000 - 120.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Medical/Dental/Vision/Life Insurance

Paid holidays and PTO

401(k) plan

Long-term/Short-term Disability

Paid Parental Leave

Employee Stock Purchase Plan

Descripción de la vacante

Cognizant is hiring a GenAI Developer to build and deploy production-ready GenAI applications using LLMs, RAG, and AI agents. You will leverage Python, LangChain, APIs, and prompt engineering to create robust solutions.

Responsibilities include developing RAG-based retrieval systems, embedding/vector database workflows, and integrating LLMs across cloud platforms (Azure OpenAI, AWS Bedrock, Vertex AI). Prior experience with LLMOps and observability is preferred.

Formación

• Strong hands-on experience with Python, LangChain/LangGraph, APIs, and prompt engineering.
• Develop RAG solutions using embeddings, vector databases, semantic search, and document retrieval.
• Integrate LLMs through platforms such as Azure OpenAI, AWS Bedrock, or Google Vertex AI.
• Experience with LLMOps/MLOps, evaluation, guardrails, observability, and cloud deployment preferred.

Responsabilidades

• Build and deploy production-ready GenAI applications.
• Implement RAG and document retrieval solutions.
• Integrate LLMs with major cloud platforms (Azure OpenAI, AWS Bedrock, Vertex AI).
• Ensure observability, evaluation, guardrails, and deployment pipelines.

Herramientas

LangChain/LangGraph

APIs

Azure OpenAI

AWS Bedrock

Google Vertex AI

LLMOps / MLOps

Descripción del empleo

Cognizant is hiring a GenAI Developer to build and deploy production-ready GenAI applications using LLMs, RAG, and AI agents. You will leverage Python, LangChain, APIs, and prompt engineering to create robust solutions.

Responsibilities include developing RAG-based retrieval systems, embedding/vector database workflows, and integrating LLMs across cloud platforms (Azure OpenAI, AWS Bedrock, Vertex AI). Prior experience with LLMOps and observability is preferred.