Description

You will design and implement end-to-end Generative AI architectures and production-grade LLM applications.

This role is on-site.

Responsibilities

• Build GenAI applications using RAG techniques, LangChain, LlamaIndex, and vector databases.
• Fine-tune Open Source LLMs using Hugging Face Transformers and PyTorch Lightning.
• Architect LLMOps pipelines using Kubernetes, Docker, and CI/CD tools like GitHub Actions.
• Engineer data pipelines for AI using Apache Spark, Kafka, and Airflow.
• Implement GenAI guardrails, including prompt injection prevention and bias detection tools.

Required Skills

• 10+ years of professional experience.
• Expertise in Python and GenAI application development.
• Hands-on experience with LangChain, LlamaIndex, LangFlow, or Flowise.
• Proficiency with Vector Databases including Pinecone, Weaviate, or Qdrant.
• Experience fine-tuning OSS LLMs such as Llama2, Mistral, GPT-Neo, or GPT-J.
• Deep understanding of tokenization using SentencePiece or Hugging Face Tokenizers.
• Competency in LLMOps tools like Ray, MLFlow, SeldonCore, or BentoML.
• Infrastructure experience with Kubernetes, Docker, Jenkins, GitLab, and Git.
• Data engineering skills with Apache Spark, Kafka, Airflow, dbt, and NiFi.

Preferred Skills

• Knowledge of AI security, including threat modeling and prompt injection prevention.
• Familiarity with AI ethics frameworks, fairness metrics, and model interpretability.

Key Skills

Education

Any Gradute