Working hours : 8- 4 EST minimum, 9-5 EST preferred.

Background check : will be required upon selection - unnecessary for submission.

Timeframe : immediate desired, ~2 weeks delay from selection is fine.

Data/GenAI Engineer (Contractor)

Position Overview :

We are seeking experienced Data/GenAI Engineers to join our Professional Services team on a contract basis. You will work directly on client engagements delivering production grade Generative AI solutions, including conversational AI assistants, document processing automation, RAG (Retrieval-Augmented Generation) systems, and AI-powered data analytics platforms. This role requires hands-on technical execution, client interaction, and the ability to work independently within an agile delivery framework.

Primary Responsibilities :

GenAI Solution Development :

- Design and implement production-ready Generative AI applications using Amazon Bedrock, Anthropic Claude, and other foundation models

- Build and optimize RAG (Retrieval-Augmented Generation) pipelines with vector databases (Weaviate, OpenSearch, Pinecone)

- Develop AI agents and multi-agent orchestration systems using frameworks like LangChain, LlamaIndex, or custom implementations

- Create conversational AI interfaces with natural language understanding, intent detection, and context management

- Implement prompt engineering strategies, few-shot learning, and fine-tuning approaches for domain specific applications

AWS Cloud Architecture & Development :

- Build serverless architectures using AWS Lambda, API Gateway, Step Functions, and EventBridge

- Design and implement data pipelines for AI model training, inference, and feedback loops

- Develop RESTful APIs and WebSocket connections for real-time AI interactions

- Configure and optimize AWS services including S3, DynamoDB, RDS, SQS, SNS, and CloudWatch

- Implement infrastructure-as-code using CloudFormation, CDK, or Terraform

Data Engineering & ML Operations :

- Design and build data ingestion pipelines for structured and unstructured data sources

- Implement ETL/ELT workflows for data preparation, cleaning, and transformation

- Create vector embeddings and semantic search capabilities for knowledge retrieval

- Develop data validation, quality monitoring, and observability frameworks

- Optimize model inference performance, latency, and cost efficiency

Client Engagement & Delivery :

- Participate in sprint planning, daily standups, and client review sessions

- Translate business requirements into technical specifications and implementation plans

- Provide technical guidance and recommendations to clients on AI/ML best practices

- Document architecture decisions, code, and deployment procedures

- Troubleshoot production issues and implement solutions quickly

Required Technical Skills (Priority Order) :

Tier 1 - Critical Must-Haves :

- Amazon Bedrock : Hands-on experience with foundation models (Claude, Nova, Llama or others), model invocation, streaming responses, and guardrails

- Agent Frameworks & Orchestration : Production experience with LangChain, LlamaIndex, Bedrock Agents, or custom multi-agent orchestration systems

- Python : Advanced proficiency with modern Python (3.9+), including async/await, type hints, and testing frameworks (pytest, unittest)

- AWS Lambda & Serverless : Production experience building event-driven architectures, function optimization, and cold start mitigation

- Vector Databases : Practical experience with at least one: Weaviate, OpenSearch, Pinecone, Chroma, or FAISS for semantic search

- LLM Integration : Direct experience with LLM APIs (Anthropic, OpenAI, Cohere), prompt engineering, and response parsing

- API Development : RESTful API design and implementation using FastAPI, Flask, or similar frameworks

Tier 2 - Highly Valuable :

- Amazon Bedrock AgentCore : Experience with AgentCore Runtime, Memory, Gateway, and Observability for building production agent systems

- AWS API Gateway : Configuration, authorization, throttling, and integration with Lambda/backend services

- DynamoDB : NoSQL data modeling, single-table design, GSI/LSI optimization, and DynamoDB Streams

- AWS Step Functions : Workflow orchestration for complex AI pipelines and multistep processes

- Docker & Containers : Containerization, ECR, ECS/Fargate deployment for AI workloads

- Data Processing : Experience with Pandas, PySpark, AWS Glue, or similar data transformation tools

Tier 3 - Strong Differentiators :

- RAG Architecture : End-to-end RAG system design including chunking strategies, retrieval optimization, and context management

- Embedding Models : Working knowledge of text embeddings (Bedrock Titan, OpenAI, Cohere) and embedding optimization

- AWS S3 & Data Lakes : S3 event notifications, lifecycle policies, and data lake architecture patterns

- CloudWatch & Observability : Logging, metrics, alarms, and distributed tracing for AI applications

- IAM & Security : AWS security best practices, least privilege access, secrets management (Secrets Manager, Parameter Store)

- CI/CD Pipelines : Experience with CodePipeline, GitHub Actions, or GitLab CI for automated deployments

Tier 4 - Nice to Have :

- SageMaker : Model training, deployment, endpoints, and feature stores

- OpenSearch : Full-text search, vector search, and hybrid search implementations

- EventBridge : Event-driven architectures and cross-service integrations

- WebSockets : Real-time bidirectional communication for streaming AI responses

- AWS CDK - Infrastructure-as-code using Python or TypeScript CDK constructs

- Fine-tuning & Training : Experience with model fine-tuning, PEFT methods, or custom model training

Required Experience & Qualifications :

- 5+ years of software engineering experience with at least 2+ years focused on AI/ML, data engineering, or cloud-native development

- 2+ years of hands-on AWS experience with production deployments

- 1+ years of direct Generative AI experience (LLMs, embeddings, RAG, agents)

- Proven track record delivering production AI applications from concept to deployment

- Strong understanding of software engineering best practices (version control, testing, code review, documentation)

- Experience working in agile/scrum environments with distributed teams

- Excellent problem-solving skills and ability to work independently with minimal supervision

- Strong written and verbal communication skills for client-facing interactions

Preferred Qualifications :

- AWS Certifications : Solutions Architect Associate/Professional, Machine Learning Specialty, or Developer Associate

- Background in healthcare, financial services, or regulated industries with understanding of compliance requirements (HIPAA, PCI-DSS, SOC 2)

- Contributions to open-source AI/ML projects or published technical content

- Experience with multi-tenant SaaS architectures and data isolation patterns

- Knowledge of cost optimization strategies for AI workloads (model selection, caching, batching)

- Familiarity with frontend frameworks (React, Angular) for building AI-powered UIs

Project Examples You May Work On :

- Building conversational AI assistants for customer service automation using Bedrock and Anthropic Claude

- Implementing RAG systems for document processing, classification, and intelligent search

- Developing AI-powered data extraction and validation pipelines for healthcare claims processing

- Creating multi-agent systems for complex workflow automation and decision support

- Building integration marketplaces connecting AI capabilities to third-party platforms

- Designing voice AI solutions using Amazon Connect and Polly for customer engagement

- Implementing AI-driven content recommendation and personalization engines