Python / GenAI / AWS Engineer

Senior Python / GenAI / AWS Engineer

Location - Moline, IL- local or relocation will work too

client- John Deere

rate- $62hr C2C

Visa- NO H1-B

Overview

We are seeking a highly skilled engineer with deep expertise in Python, Generative AI, and AWS cloud services. The ideal candidate will design and develop scalable backend systems, agentic AI frameworks, and cloud-native architectures to support intelligent, retrieval-augmented applications.

Key Responsibilities

Generative AI & Agentic Frameworks

Design and implement advanced RAG (Retrieval Augmented Generation) architectures.

Develop multi-agent workflows using LangChain, LangGraph, and MCP (Agentic Framework).

Optimize retrieval pipelines, context routing, and grounding strategies for LLM-based applications.

Apply prompt engineering and evaluation techniques to improve AI system performance.

Backend Engineering

Develop robust and scalable backend services using:

Python

FastAPI

Build APIs and microservices to support AI-driven workloads.

Ensure high-quality code design, documentation, and maintainability.

Data Engineering & Pipelines

Build data ingestion and processing workflows for structured and unstructured content.

Parse and transform XML (PDF/HTML experience is a plus).

Design indexing strategies for advanced search and retrieval systems.

Manage data processing pipelines for storing and querying content efficiently.

Cloud Architecture & DevOps (AWS)

Architect and implement cloud-native systems using:

Lambda

RDS

OpenSearch

S3

SQS

DynamoDB

ECS / EC2 / ECR

API Gateway

Maintain cloud infrastructure with high availability, scalability, and cost efficiency.

Implement CI/CD workflows and follow cloud security best practices.

Required Skills & Qualifications

Strong proficiency in Python and modern backend frameworks.

Expertise with FastAPI for API and service development.

Hands-on experience with Generative AI, RAG systems, and agentic frameworks (LangChain, LangGraph, MCP).

Strong understanding of vector stores, embeddings, semantic search, and retrieval pipelines.

Deep experience with AWS services listed above.

Solid understanding of data engineering patterns, including document processing and ingestion pipelines.

Experience designing distributed, cloud-native systems.

Preferred Qualifications

Experience with XML, PDF, or HTML document processing.

Background in enterprise or knowledge-management systems.

Familiarity with AI evaluation tools, prompt optimization, and LLM observability.

Experience with multimodal document ingestion pipelines.