About the Role
We're expanding our AI operations team. You'll design, deploy, and monitor LLM pipelines, fine-tune models, and implement intelligent document processing (IDP) solutions for our ERP and healthcare products.
Key Responsibilities
- Design and deploy production-grade LLM chains and agents (using LangChain, LlamaIndex, or custom pipelines).
- Implement Retrieval-Augmented Generation (RAG) databases using PgVector or Pinecone.
- Fine-tune open-source models (like Llama-3 or Mistral) for domain-specific tasks.
- Develop metrics and validation pipelines to measure model accuracy, latency, and cost efficiency.
Requirements
- 3+ years of experience in ML engineering and data science.
- Hands-on experience deploying LLMs and agentic pipelines in production.
- Proficiency in Python, PyTorch/TensorFlow, and vector databases.
- Familiarity with cloud ML offerings (Vertex AI, AWS SageMaker, or RunPod).