Product Analytics Solution Architect

This role owns architectural cohesion, non-functional requirements (performance, scalability, reliability, security, cost), code quality, and delivery across all platform surfaces, and integration with upstream and downstream enterprise systems. As the platform's agentic capabilities mature, the role is the AI Solutions Architect — designing, reviewing, and governing agent, retrieval, evaluation, and safety architecture in line with enterprise architecture, security, and Responsible AI standards.

What You Will Do

Solution & Platform Architecture

• Own the end-to-end architecture: data sources → analytics library → tool/integration layer → AI agent & workflow builder.
• Define scalable, secure, reusable patterns for APIs, agent tools, event flows, and platform extensions; govern API lifecycle (versioning, backward compatibility, deprecation, contract testing).
• Own non-functional requirements: latency budgets, throughput, availability/SLOs, capacity planning, and resilience (retries, circuit breakers, graceful degradation, DR/BCP).
• Govern integrations with enterprise data sources (telemetry, service, warranty, parts, work orders) and ongoing data-warehouse migrations.
• Maintain the architecture roadmap, reference architectures, and Architecture Decision Records (ADRs); drive build-vs-buy and vendor/tooling evaluations; manage tech debt deliberately.

Data, Retrieval & Context Architecture

• Design the RAG / knowledge architecture: ingestion, chunking, embeddings, vector/hybrid search, retrieval quality, and freshness.
• Own the semantic layer, data contracts, and metadata/catalog that let the agent reliably map natural language to governed data.
• Define agent memory and context architecture (session state, short- vs long-term memory, context-window optimization, semantic caching).

AI & Agentic Architecture

• Architect the agent backbone: orchestration/planner-executor patterns, tool boundaries, memory, evaluation hooks, and guardrails; support multi-agent patterns as needed.
• Define the LLM provider strategy (cloud-hosted, self-hosted, model gateway) and a cost/FinOps architecture: model routing, caching, token economics, and budget guardrails.
• Own the LLMOps lifecycle architecture: model/prompt versioning and registries, canary/A-B rollout of prompts, model upgrade and deprecation strategy.
• Own the evaluation & observability architecture: LLM tracing (OpenTelemetry), trace stores, golden datasets, eval-in-CI, online/offline eval, drift and regression gates.
• Establish AI governance practices: design reviews, risk assessments, Responsible AI alignment, and lifecycle management of agents and prompts.

Security, Trust & Compliance

• Own the AI threat model: prompt injection, data exfiltration via tools, jailbreaks, output sanitization, and least-privilege tool authorization.
• Architect multi-tenancy, data scoping, row-level security, PII/DLP, and audit/traceability across data and prompts.
• Ensure alignment with enterprise architecture, IT controls, confidential-data handling, and emerging AI regulatory requirements (e.g., AI Act, model cards, data residency).

Agile Delivery & Technical Leadership

• Lead sprint planning, code reviews, and technical design docs; set coding standards and release cadence.
• Stay hands-on 30–50%: build reference implementations, unblock complex tickets, prototype risky areas.
• Own end-to-end troubleshooting across all platform components and integration points.
• Mentor engineers on architecture principles, integration patterns, and AI solution design; contribute to hiring, interviewing, team topology, and onboarding/enablement.

Stakeholder Collaboration & Governance

• Serve as the trusted technical advisor to the PM, sponsor, AI Center of Excellence, enterprise IT, and security partners.
• Lead or participate in architecture review boards, design-governance forums, and change-impact assessments.
• Define and report architecture success metrics (reliability, latency, cost-per-insight, eval/accuracy, adoption readiness).
• Communicate complex architectural concepts and trade-offs to technical and business audiences.

What You Have

• Education & Experience: Bachelor's or Master's in Computer Science, Engineering, or related field; 8+ years building production software, with at least 3 years as a tech lead or solutions architect on a data, analytics, or AI platform.
• Application Design & Architecture: Converts business requirements into clean, modular, well-documented technical designs and reference architectures.
• System & Technology Integration: Deep knowledge of integrating heterogeneous applications, databases, and platforms, with disciplined API/contract governance.
• Systems & Reliability Engineering: Strong grounding in distributed systems, async patterns, scalability, observability, resilience, and secure-by-design.
• Technical Troubleshooting: Anticipates, diagnoses, and resolves complex multi-system issues — including non-deterministic AI failure modes — quickly.
• Technology Advising: Advises product, engineering, and senior leadership on technology trade-offs and risk.

Core Technical & Functional Skills

• Languages & Frameworks: Expert-level Python; working knowledge of TypeScript / Node.js for full-stack reviews.
• Cloud: Production experience on AWS and/or Azure (compute, storage, networking, IAM).
• Data Platforms: Cloud data warehouse (e.g., Snowflake, BigQuery, Databricks); strong SQL; data modeling; vector stores and retrieval.
• AI / Agentic: Hands-on with LLMs, agent frameworks (Model Context Protocol, function-calling, LangChain / LlamaIndex / Semantic Kernel / Agent SDKs), RAG, context/memory design, and evaluation harnesses.
• LLMOps & Observability: Model gateways, prompt/agent registries, LLM tracing, eval pipelines, drift detection.
• DevOps: CI/CD pipelines, Git workflows, containerization, IaC concepts.
• Security: Secure-by-design mindset; AI-specific threat modeling, authorization/least-privilege, and enterprise confidential-data handling.

What Will Set You Apart

• Experience designing or governing production AI agents, copilots, or AI-enabled enterprise applications at scale.
• Strong grasp of Responsible AI, model governance, ethical AI, and emerging AI regulation.
• Prior architecture role on a multi-tenant analytics platform or developer platform.
• FinOps for LLM/compute — optimizing cost-per-query and inference spend at scale.
• Experience integrating with industrial / engineering data ecosystems.
• Recognized open-source or internal-tools contributions and architecture thought leadership.pdated

Posting Dates:

October 6, 2026 - October 19, 2026

Caterpillar is an Equal Opportunity Employer. Qualified applicants of any age are encouraged to apply

Not ready to apply? Join our Talent Community.