AI Architect
About the Role:
We are looking for a bilingual (Japanese and English) AI Architect to define and lead the technical strategy for how AI is designed, built, and deployed across our products and internal systems. To bridge business goals and engineering execution, turning ambitious AI use cases into scalable, secure, and cost-effective cloud-based production solutions. Work closely with data scientists, ML engineers, software architects, product leaders, and executives, across both Japanese-speaking and global English-speaking teams.
Key Responsibilities
Architecture and strategy
- Design end-to-end AI/ML architectures covering data ingestion, training, evaluation, deployment, and monitoring
- Define the enterprise AI roadmap, reference architectures, and technology standards
- Evaluate build-vs-buy decisions across foundation models, open-source models, and vendor platforms
Cloud architecture
- Design and lead cloud-native AI solutions on AWS, Azure, and/or GCP, using managed AI services and scalable infrastructure
- Define cloud landing zones, networking, identity and access, and security patterns for AI workloads
- Drive multi-cloud or hybrid strategies where needed, including data residency considerations
- Optimize cloud cost and performance (FinOps), including GPU capacity planning and autoscaling
Generative AI and LLM solutions
- Architect LLM-powered applications, including retrieval-augmented generation (RAG), agentic workflows, tool use, and fine-tuning
- Design evaluation frameworks, guardrails, and observability for model quality, safety, latency, and cost
- Evaluate and optimize LLM performance for Japanese-language use cases (tokenization, retrieval quality, Japanese-capable models)
- Establish prompt, context, and model management practices
Platform and MLOps
- Lead the design of scalable ML platforms: feature stores, vector databases, model registries, CI/CD for ML, and inference infrastructure
- Ensure reliability, scalability, and disaster recovery for AI systems
Governance, security, and responsible AI
- Embed security, privacy, compliance, and responsible AI principles into every solution (e.g., Japan's APPI, GDPR, SOC 2, ISMAP, the EU AI Act, and Japanese AI governance guidelines)
- Define standards for bias testing, explainability, auditability, and data governance
- Partner with legal, security, and risk teams on AI policy
Leadership and collaboration
- Serve as the technical bridge between Japanese-speaking stakeholders and global/English-speaking teams, including headquarters, vendors, and cloud providers
- Provide technical guidance and mentorship to ML engineers, data scientists, and software teams
- Translate complex AI concepts for non-technical stakeholders and executives in both languages
- Produce and review technical documentation, architecture decisions, and presentations in Japanese and English
- Run architecture reviews, proofs of concept, and vendor evaluations
- Stay current on emerging AI research, tools, and industry trends
Required Qualifications
Language skills
- Native or fluent Japanese (JLPT N1 or equivalent business-level proficiency)
- Business-level English, spoken and written (e.g., TOEIC 800+ or equivalent), able to lead meetings, write documentation, and negotiate with global teams
Experience and technical skills
- 8+ years in software or data engineering, including 4+ years designing and delivering AI/ML solutions in production
- 5+ years of hands-on cloud experience, with deep expertise in at least one major platform (AWS, Azure, or GCP) and its AI/ML services (e.g., SageMaker, Bedrock, Azure AI/OpenAI Service, Vertex AI)
- Proven experience architecting cloud-native systems: serverless, containers (Docker, Kubernetes), networking, IAM, and security best practices
- Experience with infrastructure-as-code (Terraform, CloudFormation, or Bicep) and cloud cost management
- Deep understanding of machine learning, deep learning, and modern LLM and generative AI techniques
- Hands-on experience with Python and ML frameworks such as PyTorch, TensorFlow, Hugging Face, and LangChain or LlamaIndex
- Proven experience with MLOps: CI/CD, model monitoring, and workflow orchestration
- Solid knowledge of data architecture: data lakes and warehouses, streaming, vector databases, and ETL/ELT pipelines
- Experience designing secure, scalable distributed systems and APIs
- Excellent communication, stakeholder management, and documentation skills
Preferred Qualifications
- Professional cloud certifications (e.g., AWS Solutions Architect Professional, AWS ML Specialty, Azure Solutions Architect Expert, Azure AI Engineer, Google Professional Cloud Architect or ML Engineer)
- Experience with multi-cloud or hybrid cloud architectures and cloud migration
- Experience with Japanese NLP or Japanese-language LLM applications
- Experience working with Japanese enterprise clients or in Japan-based organizations, including knowledge of local business practices
- Experience building multi-agent systems and agentic AI architectures
- Familiarity with model fine-tuning techniques (LoRA, RLHF, distillation) and inference optimization (quantization, vLLM, TensorRT)
- Background in a regulated industry such as finance, healthcare, manufacturing, or government
- Published research, patents, or open-source contributions
Key Competencies
- Systems thinking and architectural judgment
- Cross-cultural communication and bilingual stakeholder management
- Pragmatism: balancing innovation with delivery, cost, and risk
- Strong ownership and decision-making in ambiguous environments
- Ability to influence without direct authority
- Commitment to ethical and responsible AI
Additional employment information
Compensation information is accurate as of the date of this posting. Cognizant reserves the right to modify this information at any time, subject to applicable law.
Applicants may be required to attend interviews in person or by video conference. In addition, candidates may be required to present their current state or government issued ID during each interview.
Cognizant is an equal opportunity employer. Your application and candidacy will not be considered based on race, color, sex, religion, creed, sexual orientation, gender identity, national origin, disability, genetic information, pregnancy, veteran status or any other characteristic protected by federal, state or local laws.
Applicants for US based positions must be currently authorized to work for any employer in the United States. The company is unable to provide employment-based immigration sponsorship for US based positions.
If you have a disability that requires reasonable accommodation to search for a job opening or submit an application, please email [email protected] for roles based in the Americas or [email protected] for roles based in India.
About Cognizant:
Cognizant (Nasdaq: CTSH) is an AI Builder and technology services provider, bridging the gap between AI investment and enterprise value by building full-stack AI solutions for our clients. Our deep industry, process and engineering expertise enables us to build an organization’s unique context into technology systems that amplify human potential, drive tangible outcomes and keep global enterprises ahead in a fast-changing world. See how at cognizant.ai or @cognizant.











