Senior AI Engineer

We are looking for a senior AI Engineer with strong hands-on experience in RAG, embeddings, and LLM-based applications. This is a hands-on, high-ownership role. You will be responsible for designing and building RAG pipelines, managing embedding and vector search infrastructure, integrating LLM capabilities into chatbot products, and working with different types of data to build reliable, production-grade AI systems.

Responsibilities:

• Design, build, and deploy end-to-end RAG pipelines from scratch.
• Select, evaluate, and fine-tune embedding models and optimize retrieval quality.
• Work with vector databases such as Pinecone, Weaviate, Chroma, and pgvector.
• Implement advanced chunking strategies, including late chunking, to improve context fidelity and retrieval precision.
• Build data ingestion pipelines from multiple sources, including SQL/NoSQL databases, PDFs, web content, Confluence, SharePoint, and real-time APIs.
• Integrate RAG and LLM components into chatbot and conversational AI products.
• Work with LangChain, LlamaIndex, Haystack, or custom orchestration frameworks.
• Build and maintain retrieval evaluation frameworks using RAGAS, triad evaluations, and other evaluation methods.
• Improve retrieval quality using metrics such as precision, recall, and relevance.
• Deploy and monitor LLM services on AWS, GCP, or Azure.
• Implement logging, monitoring, alerting, and MLOps practices for production AI systems.
• Work closely with product and engineering teams to build reliable, low-latency AI experiences.

Requirements:

• 5+ years of overall AI/ML engineering experience, including 3+ years of hands-on LLM engineering experience.
• Proven experience designing and deploying RAG systems end-to-end.
• Strong understanding of embedding models and vector databases.
• Strong programming skills in Python.
• Hands-on experience with LangChain, LlamaIndex, Haystack, or similar LLM orchestration frameworks.
• Experience working with structured, unstructured, and real-time data sources.
• Practical knowledge of late chunking and advanced retrieval strategies.
• Experience with cloud platforms such as AWS, GCP, or Azure.
• Experience with Docker and Kubernetes.
• Strong problem-solving skills with a focus on building production-ready systems.

Good to Have:

• Experience with agentic AI frameworks such as AutoGen, CrewAI, or custom agent architectures.
• Exposure to Graph RAG or Knowledge Graphs.
• Open-source contributions in AI/ML.

Skills

LLM, LLMs, Python, RAG, large language model, large language models, retrieval augmented generation