Description:
We’re looking for a skilled and driven AI/ML Engineer to join our growing AI team. This role is ideal for someone who thrives in working with LLMs, building RAG pipelines, and deploying scalable AI solutions.
Key Responsibilities:
- Build RAG pipelines using LangChain or LlamaIndex
- Integrate and manage vector databases like Pinecone, Weaviate, pgvector, or Qdrant
- Work with foundation model APIs (OpenAI, Anthropic, Hugging Face)
- Design embedding strategies and implement chunking logic
- Perform prompt engineering and orchestration
- Develop using Python and frameworks like FastAPI
- Evaluate models for accuracy, latency, and hallucination rates
- Host open-source LLMs (LLaMA, Mistral, Falcon)
- Use ML tools like MLflow, PromptLayer, and Weights & Biases
- Deploy in hybrid or on-prem environments
- Ensure secure AI implementations (PII masking, RBAC, audit logging)
- Optimize inference compute for performance
Requirements:
- 2-5 years of experience in AI/ML systems development and deployment
- Strong Python skills and hands-on with modern AI stacks
- Understanding of secure, scalable infrastructure for AI