Python Developer - Generative AI and LLM Operations

Role Overview

This position involves designing, building, and deploying cutting-edge Generative AI applications utilizing large language models (LLMs) such as GPT and Llama. The candidate will be responsible for managing comprehensive LLM pipelines including prompt engineering, fine-tuning, and integrating these models into scalable applications via APIs and microservices.

Key Responsibilities

• Develop and deploy applications leveraging Generative AI and LLM technologies.
• Build, maintain, and optimize LLM pipelines, including prompt engineering and model fine-tuning.
• Design full AI/ML workflows, covering data acquisition, model creation, and deployment processes.
• Use vector databases for semantic search and retrieval following Retrieval-Augmented Generation (RAG) architecture.
• Implement LLM operations practices for continuous model monitoring, evaluation, and version control.
• Integrate LLMs within software architectures through APIs and microservices.
• Ensure AI model performance is optimized considering cost and response latency.
• Collaborate with cross-functional teams including data engineers and product managers.
• Conduct thorough testing, validation, and debugging of developed AI models.
• Uphold security standards, compliance, and advocate for responsible AI implementation.

Required Qualifications and Skills

• Expertise in Python programming.
• Practical experience with Generative AI and LLM frameworks such as OpenAI or Azure OpenAI API, Hugging Face Transformers, LangChain, and LlamaIndex.
• Strong background in prompt engineering and Retrieval-Augmented Generation techniques.
• Familiarity with vector databases including FAISS, Pinecone, Weaviate, or Chroma.
• Basic knowledge of machine learning/deep learning libraries like PyTorch and TensorFlow.
• Experience developing RESTful APIs using FastAPI or Flask.
• Understanding of microservices architectural principles.

Preferred Additional Skills

• Experience with fine-tuning large language models using parameter-efficient methods such as LoRA or PEFT.
• Knowledge of multimodal AI involving text, images, and audio.
• Exposure to cloud service platforms including AWS, Azure, or Google Cloud Platform.
• Hands-on experience with Kubernetes and scalable application deployment.
• Familiarity with data engineering technologies like Spark and Kafka.
• Expertise in optimizing vector search and embedding strategies.
• Awareness of AI governance, ethical considerations, and regulatory compliance.
• Experience with building chatbots, copilots, or conversational AI interfaces.