AI Architect

ThinkWise Consulting LLP; Hyderabad; On-site; INR 4,200,000 - 7,000,000; Full time

Job summary

ThinkWise Consulting LLP seeks an AI Architect to lead architecture for AI and agent capabilities in an enterprise SaaS platform focusing on data privacy, governance, and AI governance. You will guide design across workstreams, from asset discovery connectors to guardrails and orchestration.

You will mentor engineers, define standards for LLM evaluation, observability, cost and latency optimization, and reflect regulatory frameworks.

Qualifications

• 8+ years of software engineering experience with AI/ML or GenAI in production.
• Proven experience leading architecture for enterprise SaaS.
• Hands-on Python and/or Java.
• Deep expertise in LLM architecture: RAG, embeddings, prompts, routing.
• Experience with LangChain, LangGraph or Semantic Kernel.
• Knowledge of AWS/Azure AI services.
• Security, RBAC, SSO and audit logging.

Responsibilities

• Define AI and agent architecture for platform features.
• Lead design reviews across workstreams for scalability and security.
• Design data models for discovering AI assets across clouds.
• Architect AI guardrails for PII and content safety.
• Provide PRD inputs with feasibility and risk.
• Set standards for LLM eval and observability.
• Guide engineers through design and code reviews.
• Stay current with EU AI Act, NIST RMF and ISO standards.

Skills

LLM architecture

RAG

Embeddings

Vector databases

Prompt engineering

Model routing

LangChain

LangGraph

Semantic Kernel

MCP

AWS Bedrock

SageMaker

Azure OpenAI

Azure AI Foundry

RBAC / security

Education

Bachelor's or Master's degree in Computer Science, Engineering, or related field

Tools

AWS Bedrock

SageMaker

Azure OpenAI

Azure AI Foundry

LangChain

LangGraph

Semantic Kernel

Job description

As an AI Architect, you will lead the architecture of AI and agent capabilities for an enterprise-grade SaaS platform in the data privacy, data governance and AI governance space. You will guide design across multiple workstreams, from AI asset discovery connectors to agentic workflows and AI guardrails, and help shape the technical direction of new AI-led product initiatives.

Key Responsibilities:

Define the AI and agent architecture (multi-agent orchestration, tool/function calling, RAG and LLM routing) for platform features.

Lead design reviews across workstreams, ensuring consistency, scalability, security and alignment with the client's architecture standards.

Design connector data models and ingestion patterns to discover AI assets (models, datasets, agents, prompts and endpoints) across cloud, data and AI platforms.

Architect AI guardrails that detect and enforce controls for PII, toxicity, prompt injection and jailbreak attempts.

Provide technical input to product requirement documents (PRDs) and solution designs for new AI initiatives, including feasibility, effort and risk.

Define standards for LLM evaluation, observability, cost and latency optimization, and responsible AI practices.

Guide AI/ML, Data/AI and backend engineers through design, implementation and code reviews, and build reusable patterns and reference implementations.

Stay current on AI regulations and frameworks (EU AI Act, NIST AI RMF, ISO/IEC 42001) and reflect them in architecture decisions.

What You'll Bring:

Bachelor's or Master's degree in Computer Science, Engineering, or a related field, or equivalent experience.

8+ years of software engineering experience, including at least 3 years architecting AI/ML, GenAI or agentic AI solutions in production.

Proven experience leading architecture for enterprise SaaS or platform products.

Strong hands-on background in Python and/or Java.

Mandatory Skills:

Deep expertise in LLM application architecture: RAG, embeddings, vector databases, prompt engineering and model routing.

Hands-on experience with agent frameworks such as LangChain, LangGraph or Semantic Kernel, and familiarity with the Model Context Protocol (MCP).

Experience with AI services on AWS (Bedrock, SageMaker) and Azure (Azure OpenAI, Azure AI Foundry).

Experience designing AI guardrails and safety controls, such as PII detection, content moderation and prompt-injection defense.

Strong understanding of data modeling, APIs, microservices and event-driven architecture.

Knowledge of LLM evaluation and observability tools (e.g., LangSmith, Langfuse, Ragas, Arize).

Solid grounding in security, RBAC, SSO and audit logging for enterprise platforms.