Description

Responsibilities

Design, develop, and deploy Gen AI solutions using advanced LLMs like OpenAI API, Open Source LLMs (Llama2, Mistral, Mixtral), and frameworks like Langchain and Haystack.

Leverage your expertise in Transformer/Neural Network models and Vector/Graph Databases (Pinecone, Milvus, Neo4j) to build robust and scalable AI systems.

Integrate speech-to-text functionality using tools like Whisper/Google TTS to create user-friendly interfaces for chatbots and IVR systems.

Craft effective semantic search experiences by employing advanced techniques like HyDE, MMR, and LLM reranking.

Collaborate with cross-functional teams (product, engineering, design) to define project goals, identify use cases, and ensure seamless integration of Gen AI solutions into existing workflows.

Stay up-to-date on the latest advancements in Gen AI research and actively explore new tools and techniques to enhance our capabilities.

Document your work comprehensively to facilitate knowledge transfer and ensure project continuity.

Qualifications

Proven experience developing and deploying LLM-based applications.

Solid understanding of Transformer/Neural Network architectures and their application in Gen AI.

Hands-on experience with Vector/Graph Databases and their use in semantic search.

Experience integrating speech-to-text tools into AI systems.

Familiarity with OpenAI API, Open Source LLMs, and Gen AI frameworks like Langchain and Haystack.

Experience creating embeddings using MPNET and Ada models.

Proficiency in programming languages like Python (essential) and potentially others (e.g., Java, C++).

Excellent problem-solving, analytical, and critical thinking skills.

Strong communication and collaboration skills to work effectively in a team environment.

A passion for innovation and a desire to push the boundaries of what's possible with Gen AI.

Key Skills
Education

Any Graduate