Description

You will lead engineering efforts in Generative AI and Machine Learning development.

This role is on-site.

Responsibilities

• Lead technical teams and collaborate within cross-functional, offshore environments.
• Design and implement Retrieval-Augmented Generation (RAG) architectures.
• Develop AI-driven automation workflows using LangChain and Haystack.
• Build and optimize Speech-to-Text and Text-to-Speech technologies.
• Integrate OpenAI APIs and open-source LLMs into production systems.

Required Skills

• 5+ years of experience in machine learning and AI engineering.
• Deep expertise in LLMs, NLP, and Deep Learning.
• Proficiency in Python and frameworks including PyTorch, TensorFlow, and Hugging Face.
• Hands-on experience with Vector Databases such as Pinecone or Milvus.
• Practical experience with Graph Databases like Neo4j.
• Strong understanding of RAG techniques.
• Experience with LangChain and Haystack.
• Familiarity with both OpenAI APIs and open-source LLMs.

Preferred Skills

• Experience in Banking, IVR, or Conversational AI applications.
• Exposure to hybrid search techniques including HyDE, MMR, and LLM reranking.
• Familiarity with Cloud AI Services across AWS, GCP, or Azure.

Key Skills

Education

Any Gradute