Generative AI Architect

Job Title: Generative AI Architect

Experience: 10+ Years

Location: Noida, Mumbai, Pune, Chennai, Gurgaon (Hybrid)

Contract Duration: Short Term

Work Time: IST Shift

Job Purpose

We are seeking a highly skilled Generative AI Architect to lead the design, development, and deployment of cutting-edge GenAI solutions across enterprise-grade applications. This role demands deep expertise in large language models (LLMs), prompt engineering, and scalable AI system architecture, along with hands-on experience in MLOps, cloud, and data engineering.

Key Responsibilities:

• Design and implement scalable, secure GenAI solutions using LLMs such as GPT, Claude, LLaMA, or Mistral
• Architect Retrieval-Augmented Generation (RAG) pipelines using LangChain, LlamaIndex, Weaviate, FAISS, or ElasticSearch
• Lead prompt engineering and evaluation frameworks for accuracy, safety, and contextual relevance
• Collaborate with product, engineering, and data teams to integrate GenAI into existing applications and workflows
• Build reusable GenAI modules like function calling, summarization engines, Q&A bots, and document chat solutions
• Deploy and optimize GenAI workloads on AWS Bedrock, Azure OpenAI, and Vertex AI
• Ensure robust monitoring, logging, and observability using Grafana, OpenTelemetry, and Prometheus
• Apply MLOps practices including CI/CD of AI pipelines, model versioning, validation, and rollback
• Research and prototype innovations like multi-agent systems, autonomous agents, and fine-tuning methods
• Implement security best practices, data governance, and compliance protocols such as PII masking, encryption, and audit logs

Required Skills & Experience:

• 8+ years in AI/ML with at least 2–3 years in LLMs or Generative AI
• Proficient in Python with experience in Transformers (Hugging Face), LangChain, OpenAI SDKs
• Strong knowledge of vector databases like Pinecone, Weaviate, FAISS, Qdrant
• Experience working with AWS (SageMaker, Bedrock), Azure (OpenAI), and GCP (Vertex AI)
• Hands-on expertise in RAG pipelines, summarization, and chat-based applications
• Familiarity with LLM orchestration frameworks like LangGraph, AutoGen, CrewAI
• Understanding of MLOps tools: MLflow, Airflow, Docker, Kubernetes, FastAPI
• Exposure to prompt injection mitigation, hallucination control, and LLMOps practices
• Ability to evaluate GenAI solutions using BERTScore, BLEU, GPTScore
• Strong communication skills with experience in architecture leadership and mentoring

Preferred (Nice to Have):

• Experience fine-tuning open-source LLMs (LLaMA, Mistral, Falcon) using LoRA or QLoRA
• Knowledge of multi-modal AI systems (text-image, voice assistants)
• Domain-specific LLM knowledge in Healthcare, BFSI, Legal, or EdTech
• Contributions to published work, patents, or open-source GenAI projects