Technical architect-Agentic AI

Hexaware Technologies; Chennai District; On-site; INR 3,500,000 - 6,000,000; Full time

Job summary

Hexaware Technologies is seeking a Senior Architect for an AI platform focused on agentic systems. You will own end-to-end technical architecture across multi-agent orchestration, tool interfaces, safety, observability, and scalable deployment.

You will define architecture, design sandboxed tool-use layers, and establish evaluation/safety frameworks while selecting model and vector strategies. Collaboration with product teams will shape roadmaps and ensure reliable, private deployments.

Qualifications

• Experience building agentic AI platforms.
• Strong background in large language models and tool integration.
• Proven ability to design scalable AI systems with governance and safety.

Responsibilities

• Define multi-agent system architecture (planner, executor, memory, tool adapters) and governance.
• Design tool-use layer (APIs, search, code, test frameworks) with secure sandboxing.
• Establish evaluation and safety architecture with guardrails and human-in-the-loop review.
• Select model strategy (proprietary vs OSS), vector/store strategy, retrieval patterns.
• Drive platform non-functionals: reliability, latency, cost, observability, data privacy.
• Collaborate with PO/AI Lead on roadmap and technical debt; work with product teams to design, test, and deploy AI capabilities.

Skills

LangChain

LlamaIndex

Multi-agent orchestration

Tool calling

Security & Compliance

Vector databases

MLflow

Weights & Biases

Test orchestration

CI/CD integration

Agentic behavior

Test generation

Tools

FAISS

Milvus

pgvector

Job description

Own the end-to-end technical architecture for a testing agentic AI platform, including multi-agent orchestration, tool interfaces, safety, observability, and scalable deployment.

Responsibilities

• Define multi-agent system architecture (planner, executor, memory, tool adapters) and governance
• Design tool-use layer (APIs, search, code, test frameworks) with secure sandboxing, enabling agentic systems to operate via tools and feedback loops
• Establish evaluation and safety architecture (guardrails, red-teaming, policy engines) for non-deterministic behavior with human-in-the-loop review
• Select model strategy (proprietary vs OSS), vector/store strategy, and retrieval patterns
• Drive platform non-functionals: reliability, latency, cost, observability, and data privacy
• Collaborate with PO/AI Lead on roadmap and technical debt; work with product teams to design, test, and deploy AI capabilities

Technical Skills

• LLM/Agent Frameworks: LangChain, LlamaIndex, multi-agent orchestration, tool-calling, function calling
• Retrieval & Memory: Vector databases (FAISS, Milvus, pgvector), embeddings
• Evaluation/LLMOps: Prompt versioning, offline/online evaluations, MLflow, Weights & Biases (W&B), feature stores
• Security & Compliance: Data governance, PII handling, secrets management, guardrails

Domain Skills

• Software testing / QA platforms
• Test orchestration and CI/CD integration
• Agentic behavior patterns
• Test generation and coordination at scale

Experience: 16+ years

Work location: Chennai/Hyderabad/Mumbai/Pune