Generative AI Engineer â LLM & Enterprise Knowledge Systems
Job description
About the Role:
We are looking for an experienced and imaginative Generative AI Architect & Engineer to lead, design, and build cutting-edge solutions using Large Language Models (LLMs) such as OpenAI’s GPT-4/5, Google Gemini, Meta’s LLaMA, and Anthropic Claude. You will spearhead the development of a corporate-wide GenAI platform that harnesses proprietary enterprise knowledge and empowers sales, operations, and other departments with instant, contextual insights, guidance, and automation.
As the GenAI leader, you will be responsible for building scalable pipelines, integrating enterprise content repositories, fine-tuning or adapting foundational models, and creating secure and intuitive access patterns for business teams. You are passionate about creating highly usable solutions that solve real-world problems, and are fluent across architecture, implementation, and MLOps best practices.
Key Responsibilities:
- Architect and implement an end-to-end GenAI solution leveraging LLMs to serve as a contextual assistant across multiple business units.
- Develop pipelines to ingest, clean, and index enterprise knowledge (documents, wikis, CRM, chat transcripts, etc.) using RAG (Retrieval-Augmented Generation) patterns and vector databases.
- Lead fine-tuning, prompt engineering, and evaluation of LLMs, adapting open-source or commercial models to enterprise needs.
- Design a secure, scalable, API-first microservice platform, including middleware and access control, integrated into corporate systems.
- Work closely with sales, operations, and customer support teams to gather use cases and translate them into impactful GenAI features.
- Drive experimentation and benchmarking to evaluate various open and closed LLMs (OpenAI, Claude, Gemini, LLaMA, Mistral, etc.) for best performance and cost-efficiency.
- Collaborate with DevOps teams to enable MLOps workflows, CI/CD pipelines, versioning, and A/B testing for AI models.
- Contribute to technical documentation, best practices, and internal knowledge sharing.
Key Qualifications:
- 4–5+ years of hands-on experience in AI/ML product development or applied research.
- Demonstrated experience working with LLMs (OpenAI, LLaMA, Claude, Gemini, Mistral, etc.) and RAG pipelines, including vector search (FAISS, Weaviate, Pinecone, Chroma, etc.).
- Strong Python skills and experience with frameworks such as LangChain, LlamaIndex, Transformers, Ray, HuggingFace, or equivalent.
- Deep understanding of NLP, model fine-tuning, embeddings, tokenization, and content ingestion pipelines.
- Exposure to enterprise content systems (e.g., SharePoint, Confluence, Salesforce, internal wikis, etc.) and integrating with them securely.
- Solid foundation in software architecture, microservices, API design, and cloud deployments (Azure, AWS, or GCP).
- Experience with security, RBAC, and compliance practices in enterprise-grade solutions.
- Ability to lead projects independently and mentor junior engineers or data scientists.
How to Apply:
Submit your resume and a short technical project summary or portfolio (GitHub, Hugging Face, blog posts)
Skills:- Generative AI, Retrieval Augmented Generation (RAG), Prompt engineering, Natural Language Processing (NLP), OpenAI, Large Language Models (LLM) tuning, Llama, Cloudera, PEFT (Parameter-Efficient Fine-Tuning) and Model-View-View-Model (MVVM)