Position Summary:
Japanese IT company is seeking an experienced AI Engineer to design, build, evaluate, and operationalize the technical foundation of the DS/ML AI Accelerator. The successful candidate will be responsible for hands-on generative AI engineering, retrieval-augmented generation (RAG), agent workflow design, and software engineering with a strong focus on governance, traceability, and measurable delivery impact.
Position Type/Expected Hours of Work:
- Hybrid work environment (4 days a week in office)
- Temp position (Duration: October, 2026 – March 31st, 2027)
Essential Functions:
Description / Essential Functions:
Governed Knowledge and RAG
- Partner with data and business owners to onboard approved documents, data definitions, prior work, and expert knowledge into a governed knowledge base.
- Implement retrieval pipelines, metadata, taxonomy, tagging, source citations, and quality checks that make context discoverable and trustworthy.
- Create evaluation datasets and retrieval-quality metrics; diagnose relevance, grounding, completeness, and source-stewardship gaps.
- Ensure generated outputs clearly distinguish retrieved facts, inferences, assumptions, and items that need subject-matter-expert confirmation.
Agentic Product Engineering
- Design and build secure multi-agent workflows that retrieve approved context, coordinate LLM and deterministic steps, use tools safely, and produce structured, traceable outputs.
- Define explicit agent roles, tool contracts, workflow state, validation, error handling, stop conditions, and human review points for reliable multi-agent operation.
- Implement reusable prompt, workflow, and tool-orchestration patterns that improve repeatability, traceability, and usability for Data Scientists, ML Engineers, Business Analysts, Product Owners, and SMEs.
Evaluation, Delivery, and Governance
- Define and instrument technical and user-centered evaluation for agent outputs, including correctness, completeness, traceability, revision effort, latency, and cost-to-serve.
- Work in two-week agile sprints; demonstrate working increments, document technical decisions and convert pilot feedback into a prioritized backlog.
- Apply secure development practices and meet Responsible AI, security, privacy, data-governance, and enterprise review-board requirements.
- Partner with the future operating owner to define maintainable code, runbooks, monitoring, knowledge-source refresh practices, and an enhancement backlog.
Requirements
Minimum qualification:
Required Education & Experience:
- Bachelor's degree in Computer Science, Data Science, Machine Learning, or a related field, or equivalent practical experience.
- 5+ years of software, data science, machine learning, or AI engineering experience, including production-quality Python development and collaborative version-controlled delivery.
- Hands-on experience building LLM-enabled applications, RAG systems, agentic workflows, or comparable AI assistants using APIs and structured tool integrations.
- Strong Python skills and experience with modern software engineering practices: testing, code review, CI/CD, API design, documentation, and observability.
- Experience with data retrieval/indexing concepts, embeddings, vector or hybrid search, evaluation design, and quality measurement.
- Ability to turn ambiguous business problems into testable technical requirements and communicate tradeoffs to technical and nontechnical partners.
- Demonstrated commitment to responsible AI, privacy, security, and data-governance practices.
Preferred Qualifications:
- Experience with modern LLM orchestration, agent-workflow, or developer-assistance platforms.
- Experience designing LLM evaluation frameworks, guardrails, prompt/version management, telemetry, or model-risk controls.
- Experience supporting ML lifecycle workflows, feature or data documentation, model development, or ML project bootstrapping.
- Familiarity with data governance, responsible AI, access control, auditability, and human-in-the-loop review.