AI Platform Engineer

Megsoft; Northern (KY); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Megsoft is seeking an experienced software engineer to design and build production-grade AI pipelines. You will own end-to-end processes from extraction to reconciliation, ensuring traceability from every figure to its source document.

You will craft evaluation suites to gate model changes and orchestrate model selection, prompts, and cost constraints across multiple providers. You will integrate AI services into .NET Core back ends and React front ends, and monitor for drift and failure modes

Qualifications

• 5+ years of software engineering experience, with at least one AI feature shipped.
• Ability to explain how you evaluated AI feature effectiveness.
• Portfolio of shipped systems counts more here than credentials.

Responsibilities

• Document AI pipelines: extraction, validation, and reconciliation that turn source documents into structured data.
• Ensure traceability: every figure links back to its source document line.
• Develop evaluation suites and benchmarks to gate model/prompts before production.
• Orchestrate model selection, prompts, and cost/latency budgets across providers.
• Integrate AI services with .NET Core back ends and React front ends.
• Monitor drift and failure modes in live systems and triage monitors.

Skills

LLM engineering

Python

C#

Data schemas

Tools

Git

SQL Server

PostgreSQL

Azure

Azure OpenAI

Job description

Our platforms turn messy source documents into numbers an investment committee or an accountant can defend. That only works if the AI layer is engineered like production software: measured, versioned, and traceable. You own that layer.

You will design extraction and reconciliation pipelines, build the evaluation harnesses that decide whether a model change ships, and integrate the results into the .NET and React platforms our clients run every day. You work directly with the founder and the senior team; what you build goes to production with your name on it.

What you’ll own

• Document AI pipelines: extraction, validation, and reconciliation flows that turn source documents into structured, verified data.
• Traceability: every figure the platform produces links back to the document line it came from. You design and defend that guarantee.
• Evaluation: regression suites and accuracy benchmarks that gate every model or prompt change before it reaches production.
• Orchestration: model selection, prompt architecture, and cost and latency budgets across providers.
• Integration: AI services exposed cleanly to .NET Core back ends and React front ends.
• Operation: monitoring for drift and failure modes in live systems, and triaging what the monitors catch.

Technical skills

• LLM engineering: production experience with frontier model APIs (Anthropic, OpenAI, or Azure OpenAI), structured output, and retrieval.
• Languages: strong Python or C#; comfort reading and writing both.
• Data: SQL Server or PostgreSQL; designing schemas for verified, source-linked data.
• Cloud: Azure services for hosting, queues, and storage.
• Discipline: Git, code review, and testing habits that survive a regulated client’s audit.

Requirements

• 5+ years of software engineering experience, including at least one AI or LLM-powered feature shipped to real users.
• Evidence you think in evals: you can explain how you knew your last AI feature actually worked.
• A portfolio of shipped systems counts more here than credentials.

Who we are.

Megsoft is a small senior engineering firm, founded in 2012 by a U.S. military veteran, that designs, builds, and operates production platforms: for PepsiCo field teams, the NYPD, federal agencies, and the AI platform X CRE. Remote-first with headquarters in Odenton, Maryland.

Sound like
your kind of hard?