Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
MIYO GlobalPosted 13 days ago

Senior AI Engineer - LLM / RAG

Who we'd reach at MIYO GlobalFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Recruiter

In-house, owns the opening

Head of the team

Director or head of the group

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a senior engineering role in Bangalore for a Python engineer who builds production LLM and retrieval-augmented generation systems, aimed at candidates with at least five years of experience. The work centres on pulling structured, citable data out of messy documents such as PDFs, scans, tables and forms, and you will also mentor other engineers and work closely with the AI lead and product team. MIYO Global uses this team to build document-processing pipelines where accuracy is measured and checked by people as well as code.

What you’ll do

  • Design Python pipelines for document ingestion, chunking, retrieval and generation.
  • Extract structured information from PDFs, scanned records, tables and forms, with citations back to the source.
  • Build validation, guardrails, evaluation and human-review workflows that raise accuracy.
  • Develop model-independent components, agentic workflows and speech-to-text pipelines where they are needed.
  • Mentor engineers and help keep production services reliable.

What they’re looking for

  • At least five years of software engineering experience, with strong Python and production backend work such as FastAPI.
  • Experience running LLM applications in production, including tool calling and structured outputs with Pydantic.
  • Production vector database experience, with advanced RAG, hybrid retrieval and re-ranking.
  • Experience with document vision and layout models, evaluation datasets and measurable quality testing.
  • Experience leading or mentoring engineers.

Nice to have

  • LoRA or PEFT fine-tuning
  • Serving open-weight models
  • AWS
  • Asynchronous processing
  • Containers
  • Regulated document workflows
  • Qdrant experience

Skills

Questions about this role

Where is this job based?

The role is based in Bangalore, India, and is listed as onsite.

How many years of experience are required?

The posting asks for at least five years of software engineering experience, including production LLM work.

Is experience with Qdrant required?

No. Production vector database experience is required, and Qdrant is preferred.

Does this role involve mentoring?

Yes. The role includes mentoring engineers and working with the AI lead on technical direction.