Toptal
Headquarters: Remote
URL: https://www.toptal.com/
We're looking for engineers to help build and productionize AI systems that go well beyond proof-of-concept — real conversational AI, RAG pipelines, and agent architectures running on AWS Bedrock and/or Azure OpenAI, serving live traffic and real users. Whether your strength is on the AI application side (agents, RAG, orchestration) or the platform side (deployment, observability, security), this role sits at the center of turning working demos into production-grade, reliable systems. If you like being close to the frontier of agentic AI and want your work to ship rather than sit in a notebook, this is built for that.
Design, build, and deploy conversational AI systems, chatbots, and AI agents powered by large language models
Architect and ship production-grade RAG (Retrieval-Augmented Generation) systems — not prototypes, but systems serving live traffic
Build and deploy LLM applications on AWS Bedrock, Azure OpenAI, AgentCore, or equivalent platforms
Develop and orchestrate agent architectures using frameworks such as LangChain, LangGraph, or LlamaIndex
Build and maintain MCP (Model Context Protocol) server integrations to extend agent capabilities
Design and build the production service layer (Lambda, API Gateway, IAM, DynamoDB, OpenSearch, or equivalents)
Establish CI/CD pipelines and manage development, beta, and production environments
Implement observability: tracing, dashboards, per-turn cost and latency metrics, error rates, and audit trails
Implement key security controls — data-leakage protection, session isolation, auth/authz boundaries, secure prompt/response storage
Write clean, maintainable, production-quality Python across the AI application and platform stack
Monitor, evaluate, and iterate on agent, RAG, and platform performance in production
Stay current with fast-moving developments in LLMs, agentic systems, and cloud AI platforms, and bring relevant advances into the project
Proven experience building conversational AI systems, AI agents, or AI platform infrastructure in production — not personal projects or tutorials
Hands-on experience with LLM application platforms: AWS Bedrock, Azure OpenAI, AgentCore, or similar
Strong Python skills for AI application development and/or service integration
Working experience with AWS and/or Azure cloud environments
Experience with at least one of: agent orchestration frameworks (LangChain, LangGraph, LlamaIndex), RAG system design, or AWS production infrastructure (Lambda, API Gateway, IAM, DynamoDB, OpenSearch)
Experience with observability and monitoring for AI or distributed systems
Strong understanding of security, data handling, and production-readiness tradeoffs
Comfortable working in a fast-moving, evolving technical environment with pragmatic engineering judgment
Experience with MCP servers
Experience with infrastructure-as-code (CDK, CloudFormation) and CI/CD pipeline design
Experience with distributed data tools such as Apache Spark, PySpark, or AWS EMR
Experience with Amazon SageMaker or similar ML platforms
Experience with OpenSearch vector search administration for RAG workloads
Experience building data pipelines for AI evaluation and KPI extraction
Comfort working in an AI-assisted development environment using AI build and review tools
RATE: $30-$50/hr.
To apply: https://weworkremotely.com/remote-jobs/toptal-ai-platform-engineer-aws-bedrock-agentcore
Anywhere in the World
Headquarters: Remote URL: https://www.toptal.com/ About the Role Join a global company as a QA Engineer specializing in UI and API test automation. You'll be the safety net for a fast-moving...