Senior AI Engineer: RAG & Multi-Agent ML Systems

Actus Consulting Group; Plano (TX); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Japanese IT company is seeking an experienced AI Engineer to design, build, evaluate, and operationalize the technical foundation of a DS/ML AI Accelerator. The role emphasizes hands-on generative AI engineering, RAG pipelines, and agent workflows with strong governance and traceability.

Hybrid work environment with four days in the office; temporary position from October 2026 to March 31, 2027. Candidates should have 5+ years in AI/ML engineering and a solid Python background.

Qualifications

• Bachelor's degree or equivalent practical experience in CS/DS/ML.
• 5+ years in software, data science, ML, or AI engineering with production Python and version-controlled delivery.
• Hands-on experience with LLM-enabled apps, RAG, agentic workflows, using APIs and structured tool integrations.
• Strong Python skills and modern software practices: testing, code review, CI/CD, API design, observability.
• Experience with data retrieval/indexing, embeddings, vector or hybrid search, evaluation design, and quality measurement.
• Ability to translate ambiguous business problems into testable technical requirements and communicate tradeoffs.

Responsibilities

• Governed knowledge and RAG: onboard documents and data, tagging, citations, quality checks.
• Design and build secure multi-agent workflows with explicit roles, tool contracts, and human review points.
• Define evaluation, backlogs, and sprint planning; ensure secure development and governance compliance.
• Collaborate with data owners and stakeholders to ensure traceability and repeatable outputs.

Skills

Python programming

LLM orchestration

RAG systems

API design

CI/CD

Data governance

Education

Bachelor's degree in Computer Science, Data Science, ML, or related field

Tools

Git

CI/CD tools

Vector databases

Embeddings / vector search

Job description

Japanese IT company is seeking an experienced AI Engineer to design, build, evaluate, and operationalize the technical foundation of a DS/ML AI Accelerator. The role emphasizes hands-on generative AI engineering, RAG pipelines, and agent workflows with strong governance and traceability.

Hybrid work environment with four days in the office; temporary position from October 2026 to March 31, 2027. Candidates should have 5+ years in AI/ML engineering and a solid Python background.