Skip to content
View reshma449's full-sized avatar
0 followers · 3 following

Block or report reshma449

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
reshma449/README.md

Hi, I'm Reshma 👋

I am engineer who ships AI that operations teams actually trust.

I've spent 9 years bridging non-technical business users and engineering teams — currently at a global financial institution, where I take AI from pain point to production: prototype it (LLM/OCR pipelines, agent workflows, MCP integrations), prove it, then carry it through deployment, user testing, and training. ML decision-support systems

🧭 How I work

  • Human-in-the-loop by design — confidence thresholds and review queues, because "the model is usually right" isn't a governance story.
  • Baselines before models — if the LLM can't beat the regex, ship the regex.
  • Evaluation before enthusiasm — every AI feature gets a labeled set and a threshold sweep before it gets a launch date.

🛠 Toolbox

Python · SQL · PowerShell · MCP · LLM/OCR pipelines · Prompt engineering · Azure DevOps · BigQuery · Power BI · ServiceNow · Agile/Scrum · PMP

📫 Reach me

Popular repositories Loading

  1. python-brushup python-brushup Public

    1

  2. system_design- system_design- Public

  3. docintel-mcp docintel-mcp Public

    Document Intelligence MCP server: extraction, confidence-threshold routing, human review queue, and BM25 search over the Model Context Protocol

    Python

  4. program-pulse program-pulse Public

    Multi-agent program reporting: collector, analyst, and reporter agents coordinate over an A2A-style message bus to compile sprint reports

    Python

  5. reshma449 reshma449 Public

    Profile README

  6. llm-extraction-evals llm-extraction-evals Public

    An evaluation harness for document field extraction — the tooling behind two questions every AI document project must answer before go-live

    Python