Hi,

​

Our client is looking AI Solutions Engineer – Real-Time Image Processing & Generative AI for Long Term Contract project in Nashville TN below is the detailed requirements.

​

Title : AI Solutions Engineer – Real-Time Image Processing & Generative AI  

Location : Nashville TN  

Duration : Long Term  

Role Overview  

We are seeking a skilled AI Solutions Engineer with expertise in real-time image processing, Generative AI frameworks (like AutoGen), and strong understanding of retrieval techniques, neural networks, and ML fundamentals. The ideal candidate will contribute to building scalable, modular, AI-driven solutions for image discrepancy detection and reporting.

Key Responsibilities  

Real-Time Image Processing & Discrepancy Detection  

• Implement real-time workflows where image uploads to AWS S3 trigger Lambda functions for immediate discrepancy detection.  
• Prepare for high-throughput scenarios by designing scalable infrastructure with SQS and load-balanced Lambda triggers.  
• Manage image transmission by converting images to byte format with minimal preprocessing to preserve context integrity.  

GenAI & Agentic Frameworks  

• Utilize agentic frameworks (e.g., AutoGen) for modular task separation including object detection, rule retrieval, and reporting.  
• Justify design choices for modularity, scalability, maintainability, and debugging over monolithic LLM prompts.  

Retrieval-Augmented Generation (RAG)  

• Implement chunking strategies: fixed-word with overlap, semantic chunking, and rule-based segmentation.  
• Integrate semantic and hybrid retrieval approaches including Amazon Kendra, cosine similarity, and metadata filtering.  
• Build graph-based RAG pipelines by extracting data from PDFs/images and transforming it into structured knowledge graphs.  

LLM Knowledge & Application  

• Demonstrate understanding of Transformer architecture, self-attention, and token prediction mechanisms.  
• Tune model behavior using temperature settings and explain its mathematical impact on output variability.  
• Optimize prompt engineering and retrieval strategies for LLM use cases.  

Neural Networks & ML Techniques  

• Address vanishing/exploding gradients via ReLU, batch normalization, gradient clipping, and smart initialization (Xavier/He).  
• Apply optimization algorithms like SGD, Adam, RMSProp for model convergence.  
• Employ ensembling techniques like bagging and boosting to tackle overfitting and underfitting.  

Data Analysis & Preprocessing  

• Detect and manage outliers through Z-scores, IQR, and transformation techniques.  
• Assess feature dependencies using correlation matrices, chi-squared tests, and statistical hypothesis testing.  
• Interpret kurtosis values to evaluate tail distributions in datasets (mesokurtic, leptokurtic, platykurtic).  

Required Skills  

• AWS (S3, Lambda, SQS)  
• Python (Byte handling, Model endpoints)  
• Experience with AutoGen or similar agentic AI frameworks  
• LLM application with retrieval techniques (RAG, Kendra, vector DBs)  
• Strong fundamentals in ML, neural networks, and optimization  
• Data preprocessing and statistical analysis  

Nice to Have  

• Experience with OCR, image parsing, and graph-based knowledge extraction  
• Familiarity with SHAP for feature importance analysis