LLM Architect

Key Responsibilities:

- Architect and implement LLM-based solutions (RAG, fine-tuning, agents) for enterprise use cases

- Design scalable AI/ML architectures using Python

- Lead deployment of LLM workloads on AWS / Azure / GCP

- Build and optimize RAG pipelines using vector databases

- Integrate LLMs with enterprise systems via APIs and microservices

- Ensure security, governance, and cost optimization of AI platforms

- Guide teams on prompt engineering, evaluation, and model optimization

- Collaborate with business and product teams to translate requirements into AI solutions

- Mentor engineers and drive AI best practices

Skills & Experience:

- 12+ years of overall experience with strong expertise in Python

- Hands-on experience with LLMs (OpenAI, Azure OpenAI, Anthropic, Llama, etc.)

- Strong experience in RAG, embeddings, fine-tuning

- Experience with vector databases (Pinecone, FAISS, Weaviate, OpenSearch)

- Expertise in at least one cloud: AWS / Azure / GCP

- Experience deploying models using Docker, Kubernetes