Senior GenAI Engineer (7+ yrs)

Hiring: Data / GenAI Engineer (Contract – Remote) Position Details Role: Data / GenAI Engineer Experience: 7–8+ Years Work Mode: Remote Shift: EST Time Zone (Approx. 5:30 PM/6:30 PM IST Start) Contract Duration: Initial Contract (Extendable up to 6–12 Months based on performance) About the Role We are seeking experienced Data/GenAI Engineers to join our Professional Services team and deliver enterprise-grade Generative AI solutions. The ideal candidate will have strong hands-on expertise in AWS, Amazon Bedrock, LLM integrations, Agent Frameworks, RAG architectures, and cloud-native application development. You will work directly with global clients to build conversational AI assistants, document automation solutions, AI-powered analytics platforms, and production-ready GenAI applications. Key Responsibilities Generative AI & Application Development Design and develop production-ready GenAI applications using Amazon Bedrock and foundation models such as Claude, Nova, and Llama. Build and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases. Develop AI Agents and multi-agent orchestration systems using LangChain, LlamaIndex, Bedrock Agents, or custom frameworks. Implement prompt engineering, few-shot learning, and fine-tuning strategies. Develop conversational AI solutions with context management and intent recognition. Integrate LLM APIs such as OpenAI, Anthropic Claude, and Cohere. Cloud & Serverless Engineering Build serverless applications using AWS Lambda, API Gateway, Step Functions, and EventBridge. Develop scalable REST APIs and real-time AI interactions using FastAPI or Flask. Configure and optimize AWS services including S3, DynamoDB, RDS, SQS, SNS, and CloudWatch. Implement Infrastructure as Code using Terraform, CloudFormation, or AWS CDK. Data Engineering & MLOps Design and develop data ingestion pipelines for structured and unstructured data. Create ETL/ELT workflows for data preparation and transformation. Implement vector embeddings and semantic search capabilities. Build data quality, observability, and monitoring frameworks. Optimize model performance, latency, scalability, and cost efficiency. Client Engagement Participate in sprint planning, stand-ups, and client review sessions. Translate business requirements into technical solutions. Provide AI/ML best-practice recommendations to clients. Troubleshoot and resolve production issues efficiently. Maintain architecture, deployment, and operational documentation. Mandatory Skills (Tier 1) Amazon Bedrock Generative AI & LLM Integration LangChain / LlamaIndex Python (3.9+) – Async Programming, Type Hints, Testing AWS Lambda & Serverless Architecture FastAPI / Flask Vector Databases (Pinecone, Weaviate, OpenSearch, Chroma, FAISS) Prompt Engineering RAG Architecture OpenAI / Anthropic Claude APIs Preferred Skills (Tier 2) Amazon Bedrock AgentCore AWS API Gateway DynamoDB AWS Step Functions Docker, ECS, Fargate Pandas, PySpark, AWS Glue Additional Skills (Tier 3 & 4) Embedding Models (Titan, OpenAI, Cohere) S3 & Data Lake Architecture CloudWatch Monitoring & Observability IAM & AWS Security CI/CD Pipelines (GitHub Actions, GitLab CI, CodePipeline) SageMaker OpenSearch EventBridge WebSockets AWS CDK Fine-Tuning & Model Training Required Experience 7–8+ years of Software Engineering experience. 2–3+ years of AWS Production Experience. 1–2+ years of hands-on Generative AI experience. Proven experience delivering production-grade AI applications. Strong understanding of Agile/Scrum methodologies. Excellent communication and client-facing skills.