Agentic Workflow Engineer (LLM / RAG / Product Integration)
Budget: $750 – $1,500 USD
We are looking for an experienced Agentic Workflow Engineer to build and ship an in-product LLM assistant integrated into an existing visualisation application (desktop + web).
The assistant will help users clean and validate datasets, generate structured inputs, and guide workflows using safe AI tool actions.
This is a production-focused role, not experimentation — the goal is to deliver a reliable, customer-ready AI feature from prototype through release.
Client details are confidential and will be shared with shortlisted candidates.
Project Scope
You will:
- Develop an embedded LLM assistant inside a production application.
- Implement RAG pipelines over product documentation and customer knowledge sources.
- Design safe AI tool actions (data checks, transformations, API calls, template creation).
- Build evaluation and testing workflows (quality metrics, regression testing, telemetry).
- Deliver production-grade integration including auth, permissions, logging, privacy controls, and performance optimization.
- Collaborate with product/domain experts to encode real-world workflows.
Required Experience
- 5–8+ years software engineering experience.
- Proven experience shipping LLM or RAG features into production.
- Strong backend/product engineering background.
- Experience handling complex or messy datasets (CSV/JSON or similar).
Nice to Have
- Azure AI stack (Azure OpenAI, Azure AI Search).
- Desktop app integration (Electron or similar).
- Enterprise data privacy or AI governance experience.
- Industrial or mining workflow familiarity.
To Apply
Please include:
- Examples of LLM/RAG systems you have shipped to production
- Your role in delivery (architecture, backend, evaluation, etc.)
- Tech stack used
- Availability and preferred engagement model
The assistant will help users clean and validate datasets, generate structured inputs, and guide workflows using safe AI tool actions.
This is a production-focused role, not experimentation — the goal is to deliver a reliable, customer-ready AI feature from prototype through release.
Client details are confidential and will be shared with shortlisted candidates.
Project Scope
You will:
- Develop an embedded LLM assistant inside a production application.
- Implement RAG pipelines over product documentation and customer knowledge sources.
- Design safe AI tool actions (data checks, transformations, API calls, template creation).
- Build evaluation and testing workflows (quality metrics, regression testing, telemetry).
- Deliver production-grade integration including auth, permissions, logging, privacy controls, and performance optimization.
- Collaborate with product/domain experts to encode real-world workflows.
Required Experience
- 5–8+ years software engineering experience.
- Proven experience shipping LLM or RAG features into production.
- Strong backend/product engineering background.
- Experience handling complex or messy datasets (CSV/JSON or similar).
Nice to Have
- Azure AI stack (Azure OpenAI, Azure AI Search).
- Desktop app integration (Electron or similar).
- Enterprise data privacy or AI governance experience.
- Industrial or mining workflow familiarity.
To Apply
Please include:
- Examples of LLM/RAG systems you have shipped to production
- Your role in delivery (architecture, backend, evaluation, etc.)
- Tech stack used
- Availability and preferred engagement model