Roles and Responsibilities
Design, develop, enhance, and maintain complex ETL mappings, workflows, data pipelines, and UNIX/Linux shell scripts in enterprise data warehouse and data lake environments
Build and optimize batch, real-time, and near-real-time integrations using IDMC or comparable integration technologies
Develop advanced SQL and database solutions across SQL Server, Oracle, PostgreSQL, or comparable relational platforms, including performance tuning and data-quality controls
Contribute to dimensional, canonical, and integration data models, and support data warehouses and data marts
Build reusable Python, Java, or scripting components for data processing, orchestration, validation, automation, and operational support
Design and build enterprise RAG solutions that retrieve trusted content and provide grounded responses using large language models
Create and maintain knowledge ingestion pipelines covering document parsing, chunking, metadata enrichment, embedding generation, indexing, retrieval, and citation or source traceability
Work with vector databases and semantic-search technologies such as Amazon OpenSearch, PostgreSQL with pgvector, or equivalent platforms
Apply prompt engineering, hybrid search, reranking, context management, and retrieval evaluation techniques to improve answer relevance and reduce unsupported responses
Build AI-enabled document intelligence solutions for extracting, classifying, summarizing, and validating information from structured and unstructured content
Establish evaluation approaches for RAG and Generative AI solutions, including retrieval quality, answer groundedness, accuracy, latency, cost, and regression testing
Implement responsible AI and model-risk controls, including data privacy, access control, content safety, human review, auditability, monitoring, and secure handling of confidential information
Partner with architecture, security, data governance, model risk, legal/compliance, and business teams to move AI proofs of concept into supportable production services
Design and support cloud-based data and AI solutions using relevant AWS services such as S3, RDS/Aurora, Redshift, Glue, Athena, Lambda, Step Functions, EventBridge, SQS, Kinesis, EMR, Textract, Bedrock, SageMaker, OpenSearch, IAM, KMS, CloudWatch, and Secrets Manager
Design and deliver conversational “chat with data” solutions for banking use cases, enabling users to query governed structured and unstructured data through natural-language interfaces with appropriate access controls, source traceability, validation, and safeguards against unsupported responses
Build resilient, observable, and cost-conscious architectures using infrastructure-as-code, CI/CD, automated testing, logging, metrics, and alerting
Apply secure cloud engineering patterns for network connectivity, encryption, secrets, least-privilege access, service integration, and operational recovery
Provide technical knowledge and understandings across design, development, testing, implementation, release, and production-support activities
Create and review functional designs, detailed technical designs, data mappings, interface specifications, runbooks, and operational documentation
Gather and document business requirements, assess current technology and processes, and recommend practical target-state solutions
Coordinate with IT leads, developers, testers, operations, and business stakeholders to ensure deliverables meet functional, non-functional, security, and control expectations
Participate in production rollouts using change-control processes, clear documentation, stakeholder communication, and implementation validation
Resolve production defects and incidents within defined service-level expectations; lead root-cause analysis and preventive remediation
Mentor engineers, promote engineering standards, conduct design and code reviews, and encourage reusable patterns and continuous improvement
Job Requirements
Bachelors’ Degree (or foreign equivalent degree) in Information Technology, Information Systems, Computer Science, Software Engineering, or a related field. Experience in the financial services or banking industry is preferred.
Minimum Qualifications
10-15 years of hands-on experience in data engineering, ETL, databases, SQL, and UNIX/Linux environments
8+ years of data integration experience in a lead or senior engineering role, preferably within banking or financial services
6+ years of hands-on experience working as a Data Engineer, designing, developing, and supporting scalable data pipelines and data-processing solutions using AWS services
8+ years of experience with IDMC or a comparable enterprise ETL/data-integration platform, including batch and real-time or near-real-time patterns.
5+ years of hands-on programming or scripting experience using Python, Java, or a comparable language
Strong experience with one or more relational database platforms and advanced SQL, including performance tuning and troubleshooting
Working knowledge of AWS data, integration, security, and serverless services
Demonstrated understanding of Generative AI concepts, embeddings, vector search, RAG architecture, knowledge bases, prompt engineering, and LLM integration patterns
Experience producing technical designs and leading delivery through development, testing, release, and production support
Hands-on experience delivering a RAG, semantic-search, conversational AI, or enterprise knowledge-base solution from proof of concept through production
Experience with Amazon Bedrock knowledge bases or agents, Amazon SageMaker, Amazon OpenSearch, PostgreSQL/pgvector, LangChain, LlamaIndex, or comparable frameworks and platforms
Experience with document-processing services and libraries, including OCR, layout-aware extraction, chunking, metadata management, and source citation
Knowledge of LLMOps/MLOps practices, including prompt and model versioning, automated evaluation, observability, feedback loops, performance monitoring, and cost controls
Understanding of data governance, AI governance, model risk, privacy, security, and regulatory expectations relevant to financial services
Experience with ER/Studio, JIRA, enterprise schedulers such as Autosys, and Agile/Waterfall delivery methods
Experience with Big Data and streaming technologies such as Spark, Kafka, Hadoop, Hive, Kinesis, or EMR
Experience with Terraform or another infrastructure-as-code tool and CI/CD pipelines
Strong communication, facilitation, analytical, and stakeholder-management skills
Mitsubishi UFJ Financial Group (MUFG) is an equal opportunity employer. We view our employees as our key assets as they are fundamental to our long-term growth and success. MUFG is committed to hiring based on merit and organsational fit, regardless of race, religion or gender.
