Sr Software AI Engineer 3 - Context Engineering

As an AI Platform Engineer (SDE 3), you will be a key builder of the high-performance software foundation that powers our enterprise AI. While your expertise lies in distributed systems and cloud-native architecture, you will apply these skills specifically to the "Context Layer"—the specialized infrastructure required to fuel next-generation Agentic AI workflows. You will work at the intersection of systems programming and modern AI infrastructure to solve practical problems in real-time data orchestration and multi-cloud compute optimization. This is a "platform-as-a-product" role where you build the tools and SDKs that enable other engineers to build autonomous agents with ease.

Key Responsibilities

• AI Infrastructure Implementation: Contribute to the development of a high-scale, AI-ready Data Lakehouse optimized for AI Agent operations and low-latency context retrieval.

• Agentic R&D & Prototyping: Hands-on prototyping of emerging architectural patterns, such as Multi-Agent Orchestration and autonomous long-term memory management.

• Engineering Excellence: Maintain high standards for code quality and CI/CD, participating in cross-functional architecture reviews and troubleshooting complex system bottlenecks.

• Agentic Ecosystem Development: Build platform-level interfaces for agentic workflows, focusing on "Host-to-Server" communication and tool-execution environments.

• Contextual Fabric Construction: Develop systems that move beyond basic search into Reasoning-based Retrieval, helping the platform understand the intent behind an agent's query.

• Protocol Integration: Implement emerging standards like the Model Context Protocol (MCP) and Agentic RAG to ensure interoperability between the platform and various LLM providers.

Qualifications & Experience

Software Engineering & Systems

• Experience: 6+ years of software engineering experience with a focus on distributed systems.

• Core Languages: Proficiency in Java or Scala and Python.

• Framework Development: Experience building extensible APIs and libraries used by other developers.

• Software-Defined Infrastructure: A preference for building automated, software-defined infrastructure over manual configuration.

Agentic Development & AI Trends

• Agentic Design: Hands-on experience with agent development frameworks such as LangGraph or CrewAI and the transition from static RAG to Agentic RAG.

• Interoperability: Knowledge of the Model Context Protocol (MCP) and how it allows AI agents to interact with diverse data sources.

• AI-Ops: Experience building "AI-native" features, including automated LLM-based evaluations within the CI/CD pipeline.

• Safety & Governance: Understanding of Human-in-the-Loop (HITL) triggers to ensure safety in autonomous systems.

CI/CD & Cloud Operations

• GitOps & Delivery: Experience with GitOps workflows (e.g., ArgoCD or Flux) to manage versioned platform configurations and AI prompt templates.

• Infrastructure-as-Code (IaC): Proficiency in Terraform to build reusable modules that enforce organizational standards across cloud accounts.

• Modern Pipelines: Ability to design CI/CD pipelines (e.g., GitHub Actions) that integrate automated testing and security scanning.

• Cloud Mastery (AWS & Azure): Hands-on experience navigating and configuring AWS and Azure Management Consoles, including core services like IAM, EC2/VMs, and S3/Blob storage.

• Observability: Experience using OpenTelemetry (OTel) to track system performance and AI-specific success metrics.

Leadership & Education

• Collaboration: A proven track record of collaborating across autonomous teams to drive the adoption of new technologies.

• Communication: Ability to clearly communicate technical trade-offs to both fellow engineers and stakeholders.

Education: Bachelor’s or Master’s degree in Computer Science (Distributed Systems focus) preferred, or equivalent deep industry experience.