Sr Generative AI Engineer - Agentic Infrastructure

Job highlights

• Experience designing systems for production workloads rather than purely experimental or proof-of-concept environments. Disclaimer: This job posting has been aggregated from external source
• Required Experience Skills
• Experience with AWS and AWS AgentCore . . Strong understanding of modern AI interoperability and service protocols,including MCP,A2A and REST APIs .

Job Summary

Senior GenAI / Agentic Systems Engineer to design, build and operate production-grade AI systems that combine LLMs, agents, retrieval, memory and distributed cloud services.

The ideal candidate is a strong software engineer who has moved beyond GenAI experimentation and has hands-on experience taking agentic and AI-powered systems from prototype to reliable production deployments . You will work across agent orchestration, context and state management, RAG, tool integration, distributed services and cloud infrastructure, with a strong focus on reliability, security, scalability and observability.

Responsibilities

• Design and develop production-grade GenAI and agentic systems using modern LLM, agent and distributed-systems architectures.

• Build agent workflows incorporating memory, context, state and session management , ensuring agents can maintain the right information across interactions and workflows.

• Design and implement RAG pipelines , including embeddings, chunking, retrieval, reranking and integration with vector databases.

• Develop sophisticated agent orchestration using LangGraph, LangChain and AWS AgentCore .

• Build and integrate tools, APIs and external services using REST, MCP, A2A and event-driven interfaces.

• Design architectures for single-agent and multi-agent systems , including agent-to-agent coordination, delegation and workflow management.

• Develop scalable backend services using Python, TypeScript and/or Java .

• Build cloud-native services on AWS , leveraging managed services and serverless/containerized architectures where appropriate.

• Develop containerized applications and production deployment pipelines using Docker, CI/CD and infrastructure automation .

• Establish robust observability across AI and distributed systems, including logging, metrics, tracing, model/agent behavior and operational monitoring.

• Engineer for reliability, scalability, performance and fault tolerance , including graceful degradation and failure recovery for AI workflows.

• Implement enterprise-grade security and governance , including IAM, encryption, secrets management, access controls and data governance.

• Design systems that appropriately handle sensitive and regulated data, with strong controls around data access, retention, auditability and lineage .

• Collaborate with product, frontend, AI/ML, platform and DevOps teams to translate business requirements into scalable technical solutions.

• Drive technical decisions, architecture evolution, engineering standards and best practices across the GenAI platform.

• Evaluate emerging agent frameworks, protocols, models and infrastructure patterns , and determine where they provide meaningful production value.

  Required Experience Skills

• 5+ years of software engineering experience , with hands-on experience building production GenAI, agentic or distributed systems .

• Strong programming experience in one or more of Python, TypeScript or Java .

• Deep understanding of LLM and agent architectures , including prompting, tool calling, orchestration and structured outputs.

• Strong hands-on experience with agent memory, context management, state management and session management .

• Production experience with RAG, embeddings and vector databases .

• Hands-on experience with LangGraph and/or LangChain .

• Experience with AWS and AWS AgentCore .

• Strong understanding of modern AI interoperability and service protocols, including MCP, A2A and REST APIs .

• Experience designing event-driven and distributed systems .

• Experience with containers, CI/CD and cloud-native deployment practices .

• Strong understanding of observability , including logs, metrics, tracing, alerting and production diagnostics.

• Strong engineering fundamentals around reliability, security, scalability, performance and fault tolerance .

• Practical experience with AWS IAM, encryption, secrets management and data governance .

• Experience designing systems for production workloads rather than purely experimental or proof-of-concept environments.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.