Agentic AI Lead, Customer Experience & IT
astrazeneca
Job description
About the role
AstraZeneca Japan's Enterprise AI Technology Delivery team is looking for an Agentic AI Lead, a senior hands-on engineer who designs, builds, evaluates and operates GenAI and agentic AI systems used by the company's commercial, medical and field organisations. The role is mostly in code, traces and evaluation data, with about 80% coding and 20% coordination.
Key responsibilities
- Take ownership of the team's existing AI platform assets and key systems for business users, and be accountable for their reliability, cost and security.
- Work autonomously with limited supervision, provide technical direction and coaching to the team's AI engineers.
- Partner with business owners so that what gets built solves a validated business problem.
Required profile
- 5+ years building and running software in production (Python; AWS or equivalent cloud).
- 2+ years shipping LLM-based or agentic applications to real users, beyond proofs of concept.
- Experience showing an evaluation set, error analysis and the iteration it drove on a real project.
- Daily use of agentic coding tools (Claude Code, Codex or equivalent) including reviewing and testing their output.
- Experience leading a technical workstream or mentoring engineers; formal team-lead experience not required.
- Bachelor's degree in Computer Science or a related quantitative discipline, or equivalent experience.
- Japanese at business level (JLPT N2 or higher, N1 preferred); native-level Japanese for business stakeholders.
- English at business level, including technical documentation and working with global AZ teams.
Required skills
- Agent architecture: workflow vs. agent harness, tool calling, MCP, memory and context management, guardrails against prompt injection and data exfiltration.
- At least one agent framework (Bedrock AgentCore, LangGraph, OpenAI Agents SDK or equivalent).
- RAG with vector stores and retrieval over structured data via SQL.
- LLM foundations: model selection, tokenisation and cost, context window and caching, when to fine-tune or self-host.
- Production operations: observability and tracing, cost/latency optimisation, statistical regression testing in CI/CD, prompt/model versioning, infrastructure-as-code.
- Full-stack application design, data modelling, testing strategy, secure-by-design practice (dependency scanning, secrets hygiene).
- AWS in production: Lambda, ECS/Fargate, API Gateway, Bedrock, IAM.
- Nice to have: AWS certification, knowledge graphs or semantic layers (e.g. Snowflake), document-processing pipelines for Japanese material, customising agent environments, eval/tracing tooling (Langfuse, Braintrust, LangSmith), Azure OpenAI and multi-provider gateway experience.
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in 日本.
Salaries by job title
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
Une question sur cette offre ?
Posez-la ici : vous recevrez le récapitulatif de l'offre par e-mail, tout de suite.
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
astrazeneca