Staff Engineer – Generative AI
Core
Building and productionizing enterprise-grade Generative AI applications on AWS, including RAG pipelines, agentic workflows, and AI-powered assistants.
Role type
Staff Engineer – Generative AI (hands-on IC)
Builds
Production GenAI applications, backend services, APIs, orchestration layers, and evaluation pipelines for enterprise clients.
Domain
Cloud infrastructure (AWS) + Generative AI / LLMs
Deliverable
production ML models | product features
Required skills
Python, backend engineering, APIs, microservices, distributed systems, RAG, agents/tool calling/orchestration, embeddings, vector databases, AWS ecosystem (Bedrock, S3, Lambda, ECS/EKS, API Gateway, OpenSearch, RDS/Postgres, IAM, KMS, Secrets Manager, CloudWatch), system design, problem-solving
Preferred skills
LangChain, LangGraph, LlamaIndex, DSPy, Semantic Kernel, CrewAI, AutoGen, multi-agent systems, LLMOps/MLOps, Kubernetes, Docker, Terraform/CDK, frontend frameworks (React/Angular)
Technologies
Amazon Bedrock, AWS Lambda, ECS, EKS, API Gateway, OpenSearch, RDS, Postgres, IAM, KMS, Secrets Manager, CloudWatch, LangChain, LangGraph, LlamaIndex, DSPy, Semantic Kernel, CrewAI, AutoGen, Kubernetes, Docker, Terraform, CDK, React, Angular
Responsibilities
Develop and productionize GenAI applications on AWS; Build RAG pipelines, agentic workflows, and AI-powered enterprise assistants; Build backend services, APIs, and orchestration layers for GenAI systems; Own end-to-end lifecycle from prototype to production; Build and implement evaluation pipelines for GenAI systems; Ensure enterprise-grade security and responsible AI practices; Build reusable frameworks and playbooks to scale GenAI adoption; Mentor engineers on GenAI guidelines
Seniority
Staff, hands-on IC with mentorship