Senior AI Engineer

Responsibilities:

• RAG pipeline ownership: Ideate, architect, build, and deploy end-to-end RAG systems from scratch through to production.
• Embedding systems: Select, evaluate, and fine-tune embedding models; manage vector stores; and optimize retrieval quality.
• Advanced chunking: Implement late chunking and other segmentation strategies to maximize context fidelity and retrieval precision.
• Multi-source data integration: Connect and ingest from diverse sources, including SQL/NoSQL databases, PDFs, web content, Confluence, SharePoint, and real-time APIs.
• Chatbot integration: Embed RAG and LLM components into conversational AI products using LangChain, LlamaIndex, or custom orchestration layers.
• Evaluation and quality: Own retrieval evaluation frameworks (RAGAS, triad evaluations) and iterate on pipelines based on precision, recall, and relevance metrics.
• Deployment and observability: Deploy and monitor LLM services on cloud infrastructure with robust logging, alerting, and MLOps practices.
• Collaboration: Partner with product and engineering teams to deliver low-latency, reliable AI experiences at scale.

Requirements:

• 4+ years of total engineering experience, with 2+ years in LLM or NLP engineering.
• Hands-on experience designing and deploying RAG systems end-to-end.
• Deep familiarity with embedding models (OpenAI Ada, Cohere, BGE, E5) and vector databases (Pinecone, Weaviate, Chroma, pgvector).
• Strong command of Python and LLM orchestration frameworks (LangChain, LlamaIndex, Haystack).
• Experience working with multiple data source types: structured, unstructured, and real-time.
• Practical knowledge of late chunking and other advanced retrieval strategies.
• Familiarity with cloud deployment (AWS / GCP / Azure) and containerization (Docker, Kubernetes).
• Strong problem-solving instincts and a bias for building things that work in production.

What You'll Own / Deliver:

• End-to-end RAG pipelines from data source to retrieval to response.
• Embedding infrastructure and vector store management.
• Integration of LLM components into live chatbot and AI products.
• Evaluation and continuous improvement of retrieval quality.
• Technical documentation and knowledge sharing across the team.

Good to Have:

• Experience with agentic frameworks (AutoGen, CrewAI, or custom agents).
• Exposure to graph-based RAG or knowledge graph integration.
  • Open-source contributions in the AI/ML space.