Position Details: Solution Architect AI

We are looking for a hands-on Platform Architect who will design and build the Knowledge Fabric Enablement Layer — the foundational system that allows teams to define, register, manage, and operationalize enterprise knowledge for Agentic AI. This role focuses on building the infrastructure, APIs, and orchestration capabilities that make knowledge integration, reasoning, and retrieval possible at scale.

You will architect the services, abstractions, and developer interfaces that let others plug in their own data, ontologies, and retrieval logic — while ensuring consistency, observability, and governance across the enterprise.

Key Responsibilities:

- Design the Knowledge Fabric Platform Services

Architect and build the underlying services that manage registration, discovery, and access of knowledge assets (e.g., ontologies, embeddings, graphs, data connectors, schemas).

- Develop Knowledge APIs and SDKs

Define and implement APIs, SDKs, and connectors for integrating knowledge sources, vector stores, and graph systems into the platform — enabling agent and workflow-level consumption.

- Implement Fabric Orchestration Layer

Build orchestration components for ingestion, transformation, indexing, and synchronization of knowledge entities across internal and external systems.

- Enable Ontology Lifecycle Management

Provide tooling and pipelines for ontology versioning, schema evolution, and entity linking so teams can evolve their domain models without disruption.

- Governance & Observability Enablement

Build modules that capture metadata, lineage, and provenance for every knowledge operation — integrating with policy, audit, and TRiSM layers.

- Performance & Scalability Engineering

Design for low-latency retrieval and high-throughput ingestion across hybrid and distributed knowledge sources.

- Collaboration & Developer Experience

Work closely with AI platform engineers, data fabric teams, and agent developers to ensure the knowledge fabric SDK and APIs are usable, composable, and extensible.

Qualifications:

• Bachelor's or master’s degree in computer science, Engineering, or a related field.

• Experience in architecture roles with a focus on manufacturing and industrial applications.

• 7+ years in distributed systems or platform engineering, with 3+ years in AI/Knowledge/ML infrastructure.

• Strong expertise in microservices, event-driven systems, and API platform design.

• Hands-on experience with one or more of:

• Vector DBs / Graph Stores: Weaviate, Neo4j, ArangoDB, RedisGraph, Milvus.

• Knowledge/Metadata Services: OpenMetadata, DataHub, Amundsen, or custom catalog services.

• Orchestration & Pipelines: Airflow, Dagster, Ray, LangGraph, or similar.

• Skilled in Python, Go, or TypeScript, with strong fundamentals in API development, caching, and messaging systems (Kafka, SQS, etc.).

• Familiarity with retrieval architectures (RAG, hybrid retrieval) and semantic search design principles.

• Experience embedding governance and policy hooks (RBAC, lineage, audit) in data or AI pipelines.

• Proficient in traditional and modern architectural patterns, software development, and system integration.

• Demonstrated ability to think strategically and integrate a broad range of ideas regarding product development.

• Excellent communication and interpersonal skills, with the ability to work effectively with cross-functional teams and manage stakeholder expectations.

• Proven leadership abilities and experience in working with diverse and globally distributed teams.

Preferred Qualifications:

• Experience with Generative, DL/ML/AI, IoT, and data analytics in a manufacturing environment.

• Certifications in cloud architecture (AWS Certified Solutions Architect, Google Cloud Professional Architect, etc.).

• Prior experience in agile development environments.

• Familiarity with multi-agent orchestration frameworks (LangGraph, ServiceNow Agentic AI, Azure Foundry, Bedrock AgentCore).

• Prior experience designing developer platforms or internal PaaS for AI or knowledge systems.

• Exposure to policy enforcement and observability (OpenTelemetry, SPIFFE/SPIRE, OPA).

• Experience with schema/ontology evolution tooling and event-driven synchronization patterns

#LI-MG2