Senior Architect : AI

Infosys; Bengaluru; On-site; INR 4,000,000 - 8,000,000; Full time

Job summary

Infosys is seeking a Senior AI Architect in India to drive the design and delivery of production-ready Generative AI solutions. The role focuses on LLM-powered chatbots, RAG pipelines, and multi-agent workflows, leveraging LangChain, LangGraph, and enterprise AI frameworks.

You will define AI architecture, GenAI strategy, and transformation initiatives, collaborating with data scientists, ML engineers, architects, and business stakeholders to deliver scalable, secure AI solutions.

Qualifications

• Hands-on experience with Generative AI and Large Language Models (LLMs).
• Experience with OpenAI GPT-4o, Claude, Llama, and open-source LLMs.
• Deep understanding of RAG architecture, LLM-based summarization, search, and content generation.
• Expertise in prompt engineering, prompt tuning, and LLM optimization.
• Experience building agentic AI systems and multi-agent workflows.

Responsibilities

• Architect and deliver Generative AI solutions using LLMs, RAG architectures, and agentic AI frameworks.
• Develop production-ready GenAI solutions including RAG pipelines and LLM-powered chatbots.
• Lead GenAI strategy and enterprise AI transformation initiatives.
• Lead prompt engineering, evaluation, benchmarking, and LLM fine-tuning.
• Integrate GenAI APIs into enterprise apps via microservices and APIs.

Skills

Generative AI

LLMs

Agentic AI

LangChain LangGraph

Vector databases

GenAIOps

Tools

Pinecone

PGVector

Azure AI Search

Amazon Titan

SageMaker

Vertex AI

LangChain

LangGraph

Job description

Experience: 10+ years overall, 3–5+ years in hands‑on AI/LLM/GenAI

We are looking for a Senior AI Architect in India with strong hands‑on experience in Generative AI (AI, Gen AI, Agentic AI, AI on Hyperscaler platforms (Azure, AWS), MCP, Gen AI Frameworks, AI Coding Tools (Devin, Claude, GHCP), and enterprise‑scale retrieval architectures.

This role focuses on building production‑ready GenAI solutions, including RAG pipelines, LLM‑powered chatbots, multi‑agent AI workflows, and LLM orchestration using LangChain and LangGraph.

You will play a key role in defining AI architecture, GenAI strategy, and enterprise AI transformation initiatives.

• Architect and deliver Generative AI solutions using LLMs, RAG architectures, and agentic AI frameworks
• Retrieval‑Augmented Generation (RAG)
• LLM‑based search and conversational AI
• Autonomous agents and multi‑agent systems
• Develop and optimize LLM orchestration workflows using LangChain, LangGraph, and similar frameworks
• Design and scale enterprise retrieval systems, including:
• Vector indexing and semantic search
• Reranking for accuracy and relevance
• Work hands‑on with vector databases such as Pinecone, PGVector, Azure AI Search, Amazon Titan
• Lead prompt engineering, prompt optimization, evaluation, benchmarking, and LLM fine‑tuning
• Design secure, scalable, and compliant AI architectures aligned with enterprise IT and data platforms
• Integrate LLMs and GenAI APIs into enterprise applications using microservices and APIs
• Implement GenAIOps / LLMOps / MLOps practices, including CI/CD, monitoring, guardrails, and continuous improvement
• Collaborate with data scientists, ML engineers, architects, product managers, and business stakeholders

Required Skills & Experience – GenAI, LLM, Agentic AI

Generative AI & LLM Expertise

• Strong hands‑on experience with Generative AI and Large Language Models (LLMs)
• Experience working with OpenAI GPT‑4o, Claude, Llama, and open‑source LLMs
• Deep understanding of RAG architecture, LLM‑based summarization, search, and content generation
• Expertise in prompt engineering, prompt tuning, and LLM optimization

Agentic AI & Orchestration

• Hands‑on experience building agentic AI systems
• Experience creating tool‑calling agents, autonomous agents, and multi‑agent workflows
• Strong experience with LangChain, LangGraph, or similar AI orchestration frameworks

Vector Databases & Retrieval Systems

• Experience with vector databases and semantic search platforms, including:
• Pinecone
• PGVector
• Amazon Titan
• Strong knowledge of embedding models, chunking strategies, indexing, and retrieval optimization
• Experience deploying GenAI solutions on cloud platforms:
• AWS (SageMaker, Bedrock)
• Google Cloud (Vertex AI)
• Strong understanding of enterprise AI architecture, security, governance, and responsible AI
• Experience integrating AI solutions into large‑scale enterprise systems

MLOps / GenAIOps

• Experience with LLMOps / GenAIOps pipelines
• Knowledge of CI/CD for LLM workflows, evaluation frameworks, monitoring, and AI safety layers
• Ability to collaborate across AI research, ML engineering, data, product, and business teams
• Strong communication skills to explain GenAI architecture and LLM design decisions
• Experience influencing AI strategy and architecture in enterprise environments