On our project we need ML Engineer, who worked with Azure before

Research
1

ML Engineer (LLM / MLOps / Azure)

We’re building an AI system for automated invoice processing (OCR + LLM + human-in-the-loop validation).

You’ll work on turning ML prototypes into production-grade systems:
– LLM-based document parsing
– CV/OCR pipelines
– Python services
– Azure + CI/CD (custom setup)

Requirements:
– Strong Python
– Hands-on with LLMs (transformers, prompt engineering, etc.)
– Experience shipping ML to production
– Solid CI/CD understanding

Nice to have:
– Hugging Face ecosystem
– Document AI / OCR
– Azure

Reality:
– imperfect infra
– custom pipelines
– high ownership

Remote (CET) | $4–6k

2

I can help you here. You can reach out to me at tusharrohilla70@gmail.com.

3

Hi,

I’m an AI & Full Stack Engineer with 9+ years building production ML systems in Python, focused on LLMs, OCR, and cloud deployments.

I’m excited by your automated invoice processing system that combines OCR, LLM parsing, and human-in-the-loop validation. The mix of document AI plus validation to keep accuracy high really stands out, and I like that you’re shipping in imperfect infra with custom pipelines.

One idea: add a confidence-driven routing layer that scores OCR+LLM outputs and routes only low-confidence or high-risk invoices to human review. Combine token-level confidence, semantic retrieval score, and simple rule checks to create a prioritized review queue and auto-labeling for high-confidence cases. This would cut human workload, speed throughput, and feed targeted training data back into the models.

At DuploCloud I built RAG and OCR pipelines, fine-tuned LLMs, and implemented human-in-the-loop flows that reduced manual validation by ~27% and improved automation throughput by 35%. I also deployed inference microservices and CI/CD on Azure, cutting release time by ~40%, so I can help turn prototypes into reliable production services in your stack.

I’d love to chat about applying this confidence-routing idea and helping ship your invoice pipeline.

Best Regards,
James Yarris

Feel free to reach out to me (james.yarris@proton.me)