Lead Engineer - Context Engineering (AI Platform)

Role : Lead Engineer - Context Engineering (AI Platform)

Location: Remote

Experience: 12+ Years

Role Overview

• Seeking a Lead Engineer ? Context Engineering to help establish and scale a new AI engineering discipline focused on how context is captured, managed, enriched, governed, and carried forward across AI experiences. This role sits within the AI Platform organization and is responsible for designing the foundational architecture that enables AI agents, copilots, conversational systems, and intelligent workflows to maintain relevant business context across user interactions.
• As AI solutions become increasingly agentic, context becomes a critical enterprise asset. This role will lead the design and implementation of context frameworks, memory architectures, retrieval systems, conversation state management, knowledge grounding, and personalization capabilities that enable consistent, trustworthy, and high-value AI experiences across Wealth Management, Advisor Experience, Employee Benefits, Customer Service, and Enterprise Operations.
• The ideal candidate combines expertise in software engineering, AI/LLM platforms, data architecture, retrieval systems, and distributed applications with a passion for solving complex problems around contextual awareness, AI memory, and knowledge continuity.

Key Responsibilities

Context Engineering Strategy & Architecture

• Define and establish Context Engineering as an emerging AI discipline within organizations enterprise AI Platform.
• Develop architectural standards, patterns, and best practices for context management across AI applications.
• Design scalable frameworks for conversation memory, session persistence, user personalization, and contextual state management.
• Establish enterprise patterns for short-term, long-term, episodic, semantic, and task-specific memory models.
• Lead technical strategy for contextual intelligence capabilities that improve AI response quality, accuracy, and relevance.

AI Context & Memory Management

• Design solutions that persist and retrieve contextual information across AI interactions and workflows.
• Build context orchestration mechanisms that combine user profiles, business data, transaction history, system events, and knowledge assets.
• Develop intelligent context window optimization and context compression strategies.
• Implement mechanisms for context ranking, prioritization, filtering, and relevance scoring.
• Create approaches that minimize hallucinations through effective grounding and contextual awareness.

Knowledge Retrieval & Grounding

• Architect Retrieval-Augmented Generation (RAG) and knowledge grounding frameworks.
• Design vector database strategies and semantic retrieval architectures.
• Build context assembly pipelines that dynamically gather relevant information before AI inference.
• Integrate structured and unstructured enterprise knowledge sources into AI interactions.
• Define patterns for context enrichment using business metadata and domain knowledge.

AI Agent & Multi-Agent Enablement

• Design shared memory and context-passing frameworks for AI agents.
• Enable context continuity between multiple AI agents operating within complex workflows.
• Establish approaches for agent collaboration, state sharing, and workflow orchestration.
• Define standards for context exchange between AI services and enterprise systems.
• Build reusable context services that support enterprise AI products.

Platform Engineering & Development

• Lead development of reusable context services, APIs, SDKs, and platform capabilities.
• Design cloud-native solutions supporting large-scale AI workloads.
• Develop event-driven architectures enabling context propagation across systems.
• Create observability capabilities for context quality, retrieval effectiveness, and AI performance.
• Drive engineering excellence across AI platform implementations.

Governance, Security & Compliance

• Ensure context management aligns with enterprise security and privacy requirements.
• Define governance models for AI memory retention, usage, and lifecycle management.
• Implement controls for personally identifiable information (PII), financial data, and sensitive business information.
• Partner with Risk, Security, Compliance, and Legal teams to establish responsible AI guardrails.
• Define auditability and traceability mechanisms for AI decision-making processes.

Leadership & Innovation

• Mentor engineers and architects in emerging Context Engineering practices.
• Evaluate evolving AI frameworks and technologies supporting contextual intelligence.
• Drive innovation around enterprise AI memory, contextual reasoning, and knowledge systems.
• Collaborate with AI Engineers, Data Engineers, Platform Architects, Product Owners, and Business Stakeholders.
• Contribute to long-term AI Platform and Agentic AI roadmap.

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or related field.
• 10+ years of software engineering experience.
• 4+ years designing AI/ML, Generative AI, or intelligent automation platforms.
• Strong experience building distributed cloud-native platforms on Azure.
• Deep understanding of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), vector databases, and semantic search.
• Experience with LangChain, LangGraph, Semantic Kernel, LlamaIndex, CrewAI, AutoGen, or similar frameworks.
• Strong proficiency in Python, Java, C#, or modern cloud-native development stacks.
• Experience designing APIs, event-driven systems, and microservices architectures.
• Knowledge of enterprise data architecture, metadata management, and knowledge management concepts.
• Experience implementing enterprise security and governance controls.

Preferred Qualifications

• Experience designing agentic AI platforms and multi-agent systems.
• Familiarity with MCP (Model Context Protocol) and emerging AI interoperability standards.
• Experience with vector databases such as Pinecone, Weaviate, Chroma, Qdrant, or Azure AI Search.
• Knowledge of graph databases, knowledge graphs, and semantic modeling.
• Experience supporting AI use cases within Financial Services, Wealth Management, Retirement, Benefits, or Insurance domains.
• Understanding of prompt engineering, evaluation frameworks, and responsible AI practices.
• Experience leading enterprise-wide AI platform initiatives.