Seeking a seasoned Application Developer to spearhead the creation of cutting-edge GenAI applications. This role involves building solutions from the ground up, leveraging advanced frameworks and ensuring robust performance.

The ideal candidate will possess a strong command of Python for developing efficient GenAI code and designing architectures for substantial data handling. Expertise in multi-modal LLM applications, including text, vision, and speech models, is essential. The role also requires familiarity with fine-tuning Small Language Models (SLMs) for specific domains.

We are looking for an individual proficient in integrating front-end technologies like React and Streamlit with GenAI backends, and skilled in data modernization and transformation pipelines. A deep understanding of fine-tuning techniques such as PEFT, QLoRA, and LoRA, alongside LLMOps implementation for streamlined deployment and monitoring, is crucial. Emphasis will be placed on embedding Responsible AI practices throughout the development lifecycle, fostering innovation.

Target companies include Quantiphi, Datastax, Coforge, HCL, Accenture, and Fractal.

Develop sophisticated GenAI applications using frameworks like Autogen, Crew.ai, LangGraph, LlamaIndex, and LangChain.

Write high-quality, efficient Python code for GenAI solutions and automation tools.

Design and implement architectures capable of handling extensive structured and unstructured data.

Work with multi-modal LLM applications, including text, vision, and speech models.

Fine-tune SLMs for domain-specific data and use cases.

Implement user interfaces using React, Streamlit, and AG Grid, ensuring seamless backend integration.

Design and execute data modernization and transformation pipelines to support GenAI initiatives.

Apply advanced fine-tuning techniques like PEFT, QLoRA, and LoRA to optimize LLMs.

Establish and manage LLMOps pipelines for continuous integration, deployment, and monitoring.

Ensure ethical AI practices are integrated into all development processes.

Drive innovation in GenAI solutions.

Demonstrate deep expertise in Python for building GenAI applications and automation.

Possess experience in productionizing GenAI applications beyond proof-of-concept stages, utilizing scale frameworks and tools.

Showcase proficiency in LLM frameworks such as Autogen, Crew.ai, LangGraph, LlamaIndex, and LangChain.

Have experience designing and implementing architectures for large-scale data handling.

Familiarity with multi-modal LLM applications (text, vision, speech models) is required.

Experience in fine-tuning SLMs for specific data and use cases is necessary.

Knowledge of prompt injection fallback and RCE tools like Pyrit and HAX toolkit is beneficial.

Familiarity with anti-hallucination and anti-gibberish tools such as Bleu is advantageous.

Strong knowledge of front-end technologies including React, Streamlit, AG Grid, and JavaScript.

Extensive experience with at least two cloud platforms (Azure, GCP, AWS) for deploying GenAI applications.

Mastery of fine-tuning methods such as PEFT, QLoRA, and LoRA is essential.

Strong understanding of LLMOps practices for model deployment and management.

Expertise in implementing Responsible AI principles and ensuring regulatory compliance.

Advanced skills in Retrieval-Augmented Generation (RAG) and Modular RAG architectures.

Proficiency in data modernization and transformation for GenAI applications.

Experience with OCR and document intelligence using cloud-based tools.

Experience with API integration protocols like REST and SOAP.

Expertise in building automated data curation and preprocessing pipelines.

Ability to create clear and comprehensive technical documentation.

Exhibit strong collaboration and communication skills for effective teamwork.