Technical Architect

HTC Global Services; Hyderabad; On-site; INR 3,500,000 - 6,000,000; Full time

Job summary

HTC Global Services is seeking an experienced Generative AI Architect in Hyderabad to design enterprise-grade GenAI and agentic AI solutions. The role focuses on RAG pipelines, knowledge graphs, and multi-agent orchestration to deliver production-ready AI systems.

The candidate will lead architecture standards, implement context engineering, and collaborate with business and engineering teams to ensure high-quality, scalable AI implementations.

Qualifications

• 15+ years IT experience with AI/ML or enterprise architecture.
• Hands-on in RAG, Knowledge Graphs and context engineering.
• Experience designing agentic AI systems and multi-agent orchestration.
• Hands-on with LangGraph, CrewAI and AutoGen.
• Strong knowledge of LLM evaluation, benchmarking and observability.
• Experience with spec-driven development and structured requirements.

Responsibilities

• Design and architect GenAI and agentic AI solutions for enterprise apps.
• Build advanced RAG pipelines with document retrieval, embeddings and vector databases.
• Design and implement Knowledge Graphs for contextual retrieval and reasoning.
• Apply context engineering to optimize LLM prompts, memory and context windows.
• Develop and orchestrate AI agents and multi-agent workflows using LangGraph, CrewAI and AutoGen.
• Establish LLM evaluation frameworks for accuracy and performance.

Skills

RAG

Knowledge Graphs

Context engineering

Agentic AI systems

LangGraph

CrewAI

AutoGen

LLM evaluation

Spec-driven development

Tools

Python

REST APIs

Vector databases

Graph databases

Job description

We are looking for an experienced Generative AI / Agentic AI Architect with 15+ years of overall IT experience and strong expertise in designing and implementing enterprise-grade AI solutions. The ideal candidate will have hands‑on experience in Retrieval‑Augmented Generation (RAG), Knowledge Graphs, context engineering, multi‑agent orchestration, and LLM evaluation, along with expertise in frameworks such as LangGraph, CrewAI, and AutoGen.

Key Responsibilities

• Design and architect scalable GenAI and agentic AI solutions for enterprise applications.
• Build advanced RAG pipelines integrating document retrieval, embeddings, vector databases, and reranking techniques.
• Design and implement Knowledge Graphs to enhance contextual retrieval, reasoning, and knowledge representation.
• Apply context engineering techniques to optimize LLM inputs, memory, context windows, and response quality.
• Develop and orchestrate AI agents and multi‑agent workflows using LangGraph, CrewAI and AutoGen.
• Establish LLM evaluation frameworks to measure accuracy, relevance, roundedness, reliability, and performance.
• Implement spec‑driven development practices to translate business requirements into structured specifications, workflows, and testable implementations.
• Define AI architecture standards, reusable components, security controls, and responsible AI practices.
• Collaborate with business stakeholders, engineering teams, and enterprise architects to deliver production‑ready AI solutions.
• Mentor engineering teams and provide technical leadership across GenAI and agentic AI initiatives.

Required Skills

• 15+ years of overall IT experience, with substantial experience in AI/ML, Generative AI, or enterprise solution architecture.
• Strong hands‑on expertise in RAG, Knowledge Graphs, and context engineering.
• Experience designing and implementing agentic AI systems and multi‑agent orchestration.
• Hands‑on experience with LangGraph, CrewAI, and AutoGen.
• Strong understanding of LLM evaluation, benchmarking, observability, and continuous quality improvement.
• Experience with spec‑driven development, structured requirements, and automated validation.
• Strong understanding of LLMs, embeddings, vector databases, semantic search, prompt engineering, and retrieval optimization.
• Knowledge of enterprise integration patterns, API design, scalability, data security, and deployment best practices.
• Excellent architecture, problem‑solving, communication, and stakeholder management skills.

Preferred Qualifications

• Experience deploying GenAI solutions in production environments.
• Familiarity with cloud‑based AI platforms, model serving, and MLOps/LLMOps.
• Experience with Python, REST APIs, vector search technologies, and graph databases.
• Experience leading technical teams and driving enterprise AI adoption.