AI Architect

Aurigo Software Technologies; Bengaluru; On-site; INR 5,000,000 - 7,500,000; Full time

Job summary

Aurigo Software Technologies in Bengaluru seeks an AI Architect to lead the design and evolution of enterprise-grade AI platforms and GenAI systems at scale. You will own system design, production maturity, evaluation frameworks, and governance across the organization.

Responsibilities include end-to-end LLM platform architecture, multi-agent systems, enterprise knowledge platforms, and deployment pipelines on AWS. Strong leadership and hands-on engineering skills are required.

Qualifications

• 10–15 years of experience in software engineering, AI, or data platforms (8+ years in AI/ML, 2–4 years in GenAI/LLM systems).
• Proven track record designing and deploying production-grade AI/ML systems at scale.
• Hands-on ownership of GenAI/LLM-based systems in production environments.

Responsibilities

• Define end-to-end architecture for LLM-powered platforms, copilots, and agent-based systems.
• Architect multi-agent systems integrating enterprise tools, APIs, and workflows.
• Own the design of enterprise knowledge systems powered by LLMs and vector databases.
• Implement advanced retrieval strategies (hybrid search, re-ranking, context optimization).
• Design memory, context management, and reasoning pipelines for complex workflows.
• Optimize systems for accuracy, latency, reliability, and cost at scale.
• Define and implement evaluation frameworks for RAG systems, agents, and copilots.
• Establish AI observability including traceability, monitoring, and feedback loops.
• Build guardrails, hallucination mitigation, and responsible AI controls.
• Architect deployment pipelines on AWS (Bedrock, OpenAI, and equivalent services).
• Design systems for scale, resilience, and high availability using microservices.
• Ensure production readiness: monitoring, rollback strategies, and cost optimization.
• Act as the AI/GenAI technical authority across engineering teams.
• Mentor engineers and guide teams on best practices, trade-offs, and design choices.
• Drive AI roadmap, platform vision, and enterprise adoption strategy.

Skills

Technical leadership

Architecture design

AI governance

Cross-team collaboration

Tools

LangChain

CrewAI

AutoGen

AWS

Azure

Kubernetes

Python

.NET

Vector databases

Job description

Experience: 10 to 15 years (8+ years in AI/ML, 2–4 years in GenAI/LLM systems)

About Aurigo

Aurigo is an AI-native capital program management platform trusted by over 300 customers managing more than $450 billion in capital programs across North America. With over 40,000 projects delivered, Aurigo helps organisations in transportation, water and utilities, healthcare, higher education, and government plan, build, and manage infrastructure with confidence. Recognised as one of the Top 25 AI Companies of 2024 and a Great Place to Work for three consecutive years, we leverage artificial intelligence to create smarter, more connected outcomes. At Aurigo, we don't just build software — we help shape the future of infrastructure.

Role Overview:

We are hiring an AI Architect to lead the design and evolution of enterprise-grade AI platforms and GenAI systems at scale. This is a high-impact, architecture-first role focused on solving real-world AI problems beyond POCs—owning system design, production maturity, evaluation frameworks, and governance. You will define how AI systems are built, deployed, observed, and scaled across the organization.

Key Responsibilities:

• Define end-to-end architecture for LLM-powered platforms, copilots, and agent-based systems
• Architect multi-agent systems integrating enterprise tools, APIs, and workflows

2. GenAI Platform & Knowledge Systems

• Own the design of enterprise knowledge systems powered by LLMs and vector databases
• Implement advanced retrieval strategies (hybrid search, re-ranking, context optimization)
• Design memory, context management, and reasoning pipelines for complex workflows
• Optimize systems for accuracy, latency, reliability, and cost at scale

3. Evaluation, Observability & Governance

• Define and implement evaluation frameworks for RAG systems, agents, and copilots
• Establish AI observability including traceability, monitoring, and feedback loops
• Build guardrails, hallucination mitigation, and responsible AI controls
• Architect deployment pipelines on AWS (Bedrock, OpenAI, and equivalent services)
• Design systems for scale, resilience, and high availability using microservices
• Ensure production readiness: monitoring, rollback strategies, and cost optimization

5. Technical Leadership & Strategy

• Act as the AI/GenAI technical authority across engineering teams
• Mentor engineers and guide teams on best practices, trade-offs, and design choices
• Drive AI roadmap, platform vision, and enterprise adoption strategy

Required Qualifications:

• 10–15 years of experience in software engineering, AI, or data platforms (8+ years in AI/ML, 2–4 years in GenAI/LLM systems)
• Proven track record designing and deploying production-grade AI/ML systems at scale
• Hands-on ownership of GenAI / LLM-based systems in production environments

Core Technical Expertise

• LLM orchestration, prompting strategies, and system design
• Vector databases and retrieval optimization
• Agent frameworks such as LangChain, CrewAI, AutoGen, or equivalent
• Evaluation frameworks and metrics for AI systems
• AI observability, monitoring, and performance tuning
• Cloud platforms (AWS/Azure) and container orchestration (Kubernetes)
• Python / .Net and relevant ML/AI libraries and tooling

Good to Have

• Experience building enterprise AI platforms (not just single applications)
• Exposure to AI governance, compliance, and ethical AI frameworks
• Background spanning MLOps, platform engineering, or applied AI research
• Familiarity with fine-tuning, RLHF, or model customization techniques
• Experience collaborating with business functions such as Sales, HR, Finance, or Operations

Success Metrics

• Production-grade AI systems achieving high accuracy, low latency, and controlled cost
• Well-defined evaluation and monitoring frameworks adopted across teams
• Reusable AI platform components deployed and leveraged by multiple engineering teams
• Scalable AI architecture handling enterprise-scale data volumes and workflows
• Measurable improvement in time-to-production for new AI initiatives

Why This Role Stands Out

• True architecture ownership — take AI systems to Production not only POC work
• Opportunity to define AI engineering standards and set the technical direction for the organization
• High-visibility role driving enterprise AI transformation journey in an organization that is recognized as one of the Top 25 AI Companies — AI is core to the product, not a side project