2 days ago
Mexico City, MexicoStaff+
Responsibilities
- Design and implement single-agent, workflow-based, and multi-agent AI architectures with orchestration, task decomposition, routing, tool integration, context management, and human approval mechanisms.
- Build RAG workflows, semantic search, vector retrieval, document processing, and AI-powered knowledge-management solutions.
- Design and implement scalable data ingestion, transformation, document-processing, and embedding pipelines for structured and unstructured data.
- Deploy containerized applications and data pipelines using AWS cloud services and integrate Model Context Protocol servers for secure tool access.
- Apply enterprise authentication, IAM, KMS, Secrets Manager, data governance, and PII/PHI handling practices under applicable regulatory requirements.
- Implement automated testing, data-quality validation, groundedness checks, policy controls, workflow evaluations, regression testing, logging, tracing, and production monitoring.
- Collaborate with technical stakeholders, engineering teams, clients, and MLOps teams to improve AI solution reliability and performance.
Requirements
- 5+ years of professional data engineering experience with strong Python and SQL skills for scalable pipelines, transformations, and AI integration solutions.
- Experience with AWS Textract, python-docx, PDF libraries, OpenPyXL, OCR, embeddings, vector retrieval, and semantic search using Chroma, OpenSearch, or similar technologies.
- Experience with AWS cloud services including Amazon S3 and at least one of Amazon Redshift, PostgreSQL, or DynamoDB, plus Docker-based deployment using Amazon ECR or AWS Batch.
- Understanding of RAG workflows, agentic AI architectures, agent orchestration, tool integration, and secure AI application development.
- Knowledge of AWS IAM, KMS, Secrets Manager, and secure handling of personally identifiable information and protected health information.
- Preferred experience with Databricks, Delta Lake, MLflow, Unity Catalog, PySpark, Amazon Bedrock Embeddings, LangChain, and Amazon Kendra.
- Preferred knowledge of AWS Glue, Athena, Step Functions, EventBridge, Kafka/MSK, or Kinesis.
- Preferred exposure to clinical-trial data, regulatory environments, GxP, HIPAA, or GDPR requirements.
- Preferred familiarity with Terraform and infrastructure-as-code configurations, as well as collaboration with MLOps teams on infrastructure, CI/CD pipelines, and production monitoring.
Benefits
- Hybrid work arrangement requiring three days per week in a client or Cognizant office.
- Available work locations are Guadalajara, Mexico City, Monterrey, or Queretaro, Mexico.
- Wellbeing programs and support for work-life balance.
- Working arrangements may change based on project and business or client requirements.
Tech Stack
Categories
AI ApplicationsData Engineering
About Cognizant
Cognizant is a public IT services and consulting firm that designs, builds, and runs enterprise technology, including digital engineering, cloud modernization, data/AI, and managed services. It sells consulting, systems integration, and outsourcing on multi-year engagements to large enterprises in healthcare, banking, retail, communications, and manufacturing. Founded in 1994 and headquartered in Teaneck, New Jersey, Cognizant is NASDAQ-listed (CTSH) and a Fortune 500 company.
