Specialist II - Gen AI Architect

UST; Thiruvananthapuram; On-site; INR 3,500,000 - 7,500,000; Full time

Job summary

A global technology services provider is seeking an experienced architect for multi-agent systems to lead the design and deployment of generative AI agents. This role involves integrating with enterprise platforms, implementing security measures, and optimizing performance while mentoring teams on best practices. Ideal candidates will have over 15 years of experience and expertise in cloud-native architectures and relevant frameworks such as LangChain or CrewAI.

Qualifications

• 15+ years of experience in relevant fields.
• Strong knowledge of security and compliance standards.
• Experience with API integrations and observability dashboards.
• Strong knowledge of cloud-native architecture (Docker, Kubernetes, AWS/GCP/Azure).
• Familiarity with RBAC, security frameworks, and compliance standards.
• Knowledge of vector databases (PGVector, Pinecone) and hybrid RAG strategies.

Responsibilities

• Architect multi-agent systems for orchestration and tool integration.
• Develop and deploy GenAI agents for various tasks.
• Integrate with enterprise platforms and optimize performance.
• Implement security and governance, including RBAC and audit logging.
• Mentor teams on GenAI architecture, prompt design, and best practices.
• Optimize performance and cost via prompt engineering and caching strategies.

Skills

GenAI architecture

Python

TypeScript

Cloud-native architecture

Prompt engineering

Docker

Kubernetes

AWS

GCP

Azure

RBAC

Security frameworks

Compliance standards

PGVector

Pinecone

Hybrid RAG

Orchestration

Memory management

Tools

LangChain

CrewAI

Docker

Kubernetes

AWS

GCP

Azure

PGVector

Pinecone

Job description

Role Description

• Architect multi-agent systems: Design patterns for orchestration, memory management, and tool integration using frameworks like LangChain or CrewAI.
• Develop and deploy GenAI agents for tasks such as:
• Requirement validation and auto-correction
• Test strategy and scenario generation
• Automation script generation and self-healing
• Data synthesis and performance planning
• Integrate with enterprise platforms: Ensure compatibility with workflow tools, CI/CD pipelines, and observability dashboards.
• Implement security and governance: Role-based access control, audit logging, and responsible AI guardrails.
• Optimize performance and cost: Reduce token usage, latency, and operational overhead through prompt engineering and caching strategies.
• Mentor teams on GenAI architecture, prompt design, and best practices.
• Hands‑on experience with LangChain/CrewAI, Python/TypeScript, and API integrations.
• Strong knowledge of cloud‑native architecture (Docker, Kubernetes, AWS/GCP/Azure).
• Familiarity with RBAC, security frameworks, and compliance standards.
• Knowledge of vector databases (PGVector, Pinecone) and hybrid RAG strategies.
• 15+ years of experience