AI/ML Infrastructure

• Design and implement scalable machine learning pipelines using AWS Bedrock, Lambda, and custom ML models

• Build and maintain vector database systems (LanceDB) for semantic search and embedding storage

• Develop intelligent document processing workflows with automatic embedding generation

• Implement conversational AI systems using LLMs

Backend Development

• Build robust Python backends using AWS CDK for infrastructure as code

• Develop serverless architectures with AWS Lambda & Glue for real-time data processing

• Create APIs and microservices for AI model inference and data analytics

• Implement enterprise-grade security and monitoring for AI systems

Data Engineering

• Process and analyze complex datasets including SEC EDGAR filings and financial data

• Build ETL pipelines for data ingestion from Fivetran connectors and external sources

• Implement semantic search and embedding systems for unstructured data

• Design scalable data storage solutions using S3, DynamoDB, and Athena

Enterprise Integration

• Integrate with enterprise data platforms and third-party APIs

• Build customer-facing AI agents and chatbots for business intelligence

• Implement multi-tenant architecture for enterprise customers

• Develop monitoring and alerting systems for AI model performance

‍

Core Technical Skills

• 5+ years of backend development experience with Python

• Strong experience with AWS services (Lambda, S3, DynamoDB, Bedrock, CloudWatch)

• Hands-on experience with machine learning frameworks and NLP libraries

• Experience with vector databases and semantic search technologies

• Proficiency with infrastructure as code (AWS CDK preferred)

AI/ML Expertise

• Experience with LLMs, embeddings, and transformer models

• Knowledge of sentence transformers, scikit-learn, and ML model deployment

• Understanding of RAG (Retrieval-Augmented Generation) architectures

• Experience with AWS Bedrock or similar managed AI services

• Familiarity with vector search and similarity matching algorithms

Data & Analytics

• Experience processing large-scale datasets and unstructured documents

• Knowledge of data pipelines, ETL processes, and real-time processing

• Experience with financial data, SEC filings, or regulatory documents (preferred)

• Understanding of analytics platforms and business intelligence tools

Software Engineering

• Strong experience with serverless architectures and microservices

• Proficiency with REST APIs, event-driven architectures, and async processing

• Knowledge of enterprise security patterns and multi-tenant systems

• Experience with monitoring, logging, and performance optimization