Sr.AI Engineer

Job Title:

Location:

Type:

Experience:

AI Engineer

Key Responsibilities:

• Architect and develop

  end-to-end RAG pipelines

  , combining dense and sparse retrieval (embeddings, hybrid search).
• Design and implement

  knowledge ingestion pipelines

  for structured and unstructured data (PDFs, documents, web content, APIs).
• Build

  data acquisition pipelines

  , including web scraping and system integration using tools like

  Playwright, Puppeteer, or Selenium

  .
• Optimize retriever–generator interactions using

  reranking, query rewriting, and context compression

  .
• Develop and maintain

  RAG evaluation frameworks

  (precision@k, MRR, faithfulness, hallucination metrics).
• Experiment with

  vector databases

  (Pinecone, Weaviate, Chroma, Milvus) and

  LLM APIs

  (OpenAI, Anthropic, Mistral).
• Build

  custom retrievers

  leveraging semantic, hybrid, and metadata-based filtering.
• Deploy scalable RAG systems using

  LangChain, LlamaIndex

  , and modern

  MLOps stacks

  .
• Collaborate closely with AI Engineers to improve

  grounding accuracy and response relevance

  .
• Research and apply

  state-of-the-art retrieval, ranking, chunking, and context strategies

  .
• Build and optimize

  Machine Learning and Deep Learning models

  using

  PyTorch or TensorFlow

  .

Requirements:

• Strong proficiency in

  Python

  and RAG frameworks like

  LangChain and LlamaIndex

  .
• Deep understanding of

  information retrieval

  (vector search, hybrid retrieval).
• Hands-on experience with

  vector databases

  (Pinecone, Weaviate, Chroma, Milvus, Elasticsearch).
• Solid knowledge of

  embedding models

  (OpenAI, Hugging Face, Cohere).
• Experience designing and tuning

  RAG evaluation pipelines

  .
• Strong grasp of

  LLM orchestration, prompt engineering, and context optimization

  .
• Familiarity with

  cloud-based MLOps

  (AWS, GCP, Azure) and deployment tools (

  FastAPI, Docker, Kubernetes

  ).
• Production-level Python development skills with strong

  OOP fundamentals

  .

Preferred Qualifications:

• Experience integrating retrieval systems with

  fine-tuned LLMs

  or

  domain-specific knowledge graphs

  .
• Background in

  enterprise search, chatbots, or knowledge-grounded QA systems

  .
• Publications or

  open-source contributions

  in retrieval systems or LLM evaluation.

What We Offer

• Competitive salary and performance-based incentives.
• Collaborative, growth-focused work culture.
• Opportunities for continuous learning and professional development.