GenAI Architect

Coforge; Bengaluru; On-site; INR 4,000,000 - 6,400,000; Full time

Job summary

Coforge is seeking a Generative AI Architect in Bengaluru to design and deploy scalable AI/LLM solutions, including RAG and agent-based workflows. You will lead architecture, model fine-tuning, and integration with enterprise systems, ensuring security, ethics, and cost-efficiency.

The role requires deep expertise in LLM orchestration frameworks, multi-modal tooling, and collaboration with data scientists, ML engineers, and product teams to deliver AI-driven business outcomes.

Qualifications

• 7+ years in AI/ML architecture or related role.
• Proven production experience with Generative AI and LLM-based solutions.
• Hands-on with LangChain, LangGraph or similar orchestration frameworks.
• Experience building RAG pipelines and knowledge integration.
• Strong background in TensorFlow, PyTorch, and Hugging Face.

Responsibilities

• Design and implement architectural framework for generative AI and LLM-powered solutions (RAG, agents, multi-step workflows)。
• Lead design, fine-tuning, and deployment of generative AI models and LLM-based applications for content generation, automation, copilots, and decision support.

Skills

Generative AI architecture

LLM orchestration

Prompt engineering

RAG pipelines

LangChain/LangGraph

TensorFlow/PyTorch

Cloud deployment (AWS/Azure/GCP)

Python/Java/C++

Tools

LangChain

LangGraph

Semantic Kernel

FAISS/Pinecone/Azure AI Search

Hugging Face models

GPT/DALL-E/Stable Diffusion tooling

Job description

The Generative AI Architect will be responsible for designing, developing, and implementing generative AI solutions that align with the company's strategic objectives. This role involves leading the architecture and deployment of advanced AI models, including LLM-based systems and agentic workflows, ensuring scalability, security, and ethical considerations are integrated into all AI initiatives. The ideal candidate will possess deep expertise in generative AI technologies, LLM orchestration frameworks (e.g., LangChain, LangGraph), a strong understanding of AI ethics, and the ability to collaborate effectively with cross-functional teams

Key Responsibilities

• Develop and maintain the architectural framework for generative AI and LLM-powered solutions (including RAG, agents, and multi-step workflows), ensuring alignment with business goals and technical standard
• Lead the design, fine-tuning, and deployment of generative AI models (e.g., GPT, DALL-E, Stable Diffusion) and LLM-based applications for use cases such as content generation, automation, copilots, and decision support systems

LLM Orchestration & Agent Design

• Design and implement LLM orchestration pipelines using frameworks such as LangChain, LangGraph, Semantic Kernel, or similar tools. Build agentic workflows, tool-augmented agents, and multi-step reasoning pipeline

RAG & Knowledge System

• Architect and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (e.g., FAISS, Pinecone, Azure AI Search) and embedding models to enable enterprise knowledge integration

Integration

• Collaborate with software engineering teams to integrate generative AI capabilities, LLM services, and autonomous agents into existing applications, APIs, and enterprise workflow

Scalability & Performance

• Ensure AI/LLM solutions are scalable, optimized for latency and cost, and production-ready across cloud and hybrid environment

Ethical AI Practices

• Implement and enforce ethical guidelines for AI development, including bias mitigation, explainability, safety guardrails, and responsible AI practices in LLM deployment
• Stay abreast of advancements in LLMs, prompt engineering, agent frameworks, multimodal AI, and GenAI tooling, incorporating emerging techniques into the AI strategy
• Work closely with data scientists, ML engineers, product teams, and stakeholders to identify AI-driven opportunities and ensure successful delivery

Documentation & Standard

• Create comprehensive documentation for AI architectures, LLM workflows, prompt templates, and best practices. Establish coding, evaluation, and governance standards

Experience

• Minimum of 7+ years of experience in AI/ML architecture or a related role
• Proven experience in designing and deploying Generative AI and LLM-based solutions in production
• Hands-on experience with LangChain, LangGraph, or similar orchestration frameworks for building LLM pipelines and agent systems
• Experience in building RAG pipelines, vector database integration, and prompt engineering techniques
• Strong experience with AI frameworks/tools such as TensorFlow, PyTorch, Hugging Face
• Experience with cloud platforms (AWS, Azure, GCP) and deploying scalable AI/LLM solutions

Technical Skills

• Proficiency in programming languages such as Python (preferred), Java, or C++
• Strong expertise in LLMs, prompt engineering, embeddings, and fine-tuning techniques

Hands-on experience with:

• LangChain, LangGraph / Agent frameworks
• Strong understanding of machine learning and deep learning concepts