Job Title : Generative AI Lead.
Location : Noida(Hybrid) once in a week.
Experience Required : 7+ years (including 3 years in GenAI / LLMs).
About the Role :
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 requires deep expertise in LLMs, prompt engineering, and scalable AI system architecture, combined with hands-on experience in MLOps, cloud, and data engineering.
Key Responsibilities :
- Design and implement scalable, secure GenAI solutions using large language models (LLMs) such as GPT, Claude, LLaMA, or Mistral.
- Architect Retrieval-Augmented Generation (RAG) pipelines using tools like 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 (function calling, summarization, Q&A bots, document chat, etc.
- Leverage cloud-native platforms (AWS Bedrock, Azure OpenAI, Vertex AI) to deploy and optimize GenAI workloads.
- Ensure robust monitoring, logging, and observability across GenAI deployments (Grafana, OpenTelemetry, Prometheus).
- Apply MLOps practices for CI / CD of AI pipelines, model versioning, validation, and rollback.
- Research and prototype emerging trends in GenAI including multi-agent systems, autonomous agents, and fine-tuning.
- Implement security best practices, data governance, and compliance protocols (PII masking, encryption, audit logs).
Required Skills & Experience :
8+ years of overall experience in AI / ML, with at least 23 years focused on LLMs / GenAI.Strong programming skills in Python, with frameworks like Transformers (Hugging Face), LangChain, or OpenAI SDKs.Experience with Vector Databases (e., Pinecone, Weaviate, FAISS, Qdrant).Proficiency in cloud platforms : AWS (SageMaker, Bedrock), Azure (OpenAI), GCP (Vertex AI).Experience in designing and deploying RAG pipelines, summarization engines, and chat-based apps.Familiarity with function calling, tool usage, agents, and LLM orchestration frameworks (LangGraph, AutoGen, CrewAI).Understanding of MLOps tools : MLflow, Airflow, Docker, Kubernetes, FastAPI.Exposure to prompt injection mitigation, hallucination control, and LLMOps.Ability to evaluate GenAI systems using metrics like BERTScore, BLEU, GPTScore.Strong communication and documentation skills; ability to lead architecture discussions and mentor engineering teams.Preferred (Nice to Have) :
Experience with fine-tuning open-source LLMs (LLaMA, Mistral, Falcon) using LoRA or QLoRA.Knowledge of multi-modal AI (text-image, voice assistants).Familiarity with domain-specific LLMs in Healthcare, BFSI, Legal, or EdTech.Published work, patents, or open-source contributions in GenAI(ref : hirist.tech)