Architect- AI Native Platform

About Sirion

Sirion is the world’s leading AI–native Contract Lifecycle Management (CLM) platform, transforming the end-to-end contracting journey for enterprises. With Agentic AI at the core, the platform’s extraction, conversational search, and AI-enhanced negotiation capabilities have revolutionized contracting across Fortune 500 companies like IBM, Coca Cola, Citi, and GE. With more than 800 employees across the globe, Sirion comprises a team of AI engineers, legal experts, and researchers who are building the next generation of intelligent CLM. Recognized by Gartner, IDC, and Spend Matters as a consistent CLM leader, Sirion sets the innovation benchmark for the category.

For more information, visit www.sirion.ai.

 

Role Title: Engineering Architect –(Agentic AI Platform)

Power the Future of AI & Why This Role Matters

As an Engineering Architect – (Agentic AI Platform), you will define the technical architecture powering Sirion's AI-native Contract Lifecycle Management platform. You will architect highly scalable, cloud-native backend systems that enable the next generation of intelligent, autonomous AI capabilities across contract understanding, reasoning, negotiation, workflow automation, and enterprise integrations.

This role combines deep backend engineering expertise with AI platform architecture. You will partner closely with Product, Engineering, Applied AI, Data Science, and Platform teams to build secure, resilient, and high-performance distributed systems capable of supporting enterprise-scale Agentic AI applications. You will play a key role in shaping Sirion's backend architecture, driving engineering excellence, and enabling AI-first product innovation.

 

How You'll Make an Impact

• Define and drive the architecture of Sirion's next-generation AI-native backend platform, ensuring scalability, resilience, security, and maintainability.
• Architect large-scale distributed systems, cloud-native microservices, event-driven platforms, and enterprise APIs supporting millions of contract transactions.
• Design backend platforms enabling Agentic AI capabilities including autonomous agents, multi-agent collaboration, reasoning, planning, tool orchestration, memory management, and workflow automation.
• Architect enterprise-grade Retrieval-Augmented Generation (RAG) pipelines, semantic search platforms, vector search infrastructure, and knowledge retrieval systems.
• Build highly scalable backend services supporting LLM inference, AI orchestration, model routing, prompt execution, and AI workflow management.
• Drive architecture for API gateways, service mesh, asynchronous messaging, event streaming, distributed caching, and real-time processing platforms.
• Establish engineering best practices around system design, architecture governance, scalability, observability, security, performance optimization, and operational excellence.
• Partner closely with AI Engineering teams to integrate Large Language Models, Agentic AI frameworks, and intelligent automation capabilities into production systems.
• Mentor senior engineers and technical leads through architecture reviews, design reviews, and technical leadership across multiple engineering teams.
• Evaluate emerging technologies across distributed systems, cloud platforms, AI infrastructure, backend engineering, and enterprise architecture to accelerate product innovation.

 

Skills & Experience You Bring to the Table

Required Qualifications

• 12–15 years of experience building enterprise-scale backend platforms with significant experience in software architecture or principal engineering roles.
• Bachelor's or Master's degree in Computer Science or a related engineering discipline from a Tier-1 institution.
• Deep expertise in designing distributed systems, microservices architecture, event-driven systems, Domain Driven Design (DDD), CQRS, Event Sourcing, distributed transactions, and scalable enterprise platforms.
• Strong hands-on expertise in Java (preferred), Golang, Scala, Kotlin, or Python, with extensive experience building high-performance backend systems.
• Strong experience with Spring Boot, Spring Cloud, REST APIs, gRPC, GraphQL, Reactive Programming, and enterprise integration patterns.
• Extensive experience with cloud-native technologies including Kubernetes, Docker, AWS, Azure or GCP, Infrastructure as Code, Terraform, Helm, and Service Mesh technologies.
• Strong expertise with Kafka, Pulsar, RabbitMQ, distributed messaging, event streaming, and asynchronous architectures.
• Deep understanding of SQL and NoSQL databases including PostgreSQL, MySQL, MongoDB, Cassandra, Redis, Elasticsearch/OpenSearch, and distributed data platforms.
• Experience designing high-performance systems utilizing caching strategies, distributed storage, indexing, partitioning, replication, and query optimization.
• Strong understanding of observability using Prometheus, Grafana, OpenTelemetry, ELK, distributed tracing, logging, monitoring, and production diagnostics.
• Hands-on experience building AI-enabled backend platforms leveraging Large Language Models (LLMs), Generative AI, Retrieval-Augmented Generation (RAG), Semantic Search, Vector Databases, AI Orchestration, and Agentic AI architectures.
• Experience integrating AI frameworks such as LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, Semantic Kernel, or equivalent agent orchestration platforms.
• Strong understanding of vector databases including Pinecone, Weaviate, Milvus, Qdrant, pgvector, or similar technologies.
• Experience designing secure, scalable enterprise platforms supporting AI governance, AI observability, model evaluation, guardrails, and responsible AI practices.
• Strong analytical, architectural, and stakeholder management capabilities with the ability to influence engineering strategy across multiple teams.

 

 

Preferred Qualifications

• Experience building AI-native Enterprise SaaS platforms serving Fortune 500 customers.
• Experience designing production-grade Agentic AI platforms with autonomous workflows and multi-agent architectures.
• Experience implementing Model Context Protocol (MCP), AI memory architectures, tool calling, function calling, and AI orchestration frameworks.
• Experience with MLOps platforms, model serving infrastructure, inference optimization, GPU-based deployments, and AI infrastructure engineering.
• Exposure to LegalTech, Contract Lifecycle Management (CLM), Enterprise Workflow Automation, Knowledge Management, or Intelligent Document Processing.
• Contributions to open-source projects, architecture communities, technical publications, or technology conferences.