Generative Ai Engineer - Senior

About Saarthee :

Saarthee is a Global Strategy, Analytics, Technology and AI consulting company, where our passion for helping others fuels our approach and our products and solutions. We are a onestop shop for all things data and analytics. Unlike other analytics consulting firms that are technology or platform specific, Saarthee’s holistic and tool agnostic approach is unique in the marketplace. Our Consulting Value Chain framework meets our customers where they are in their data journey. Our diverse and global team work with one objective in mind : Our Customers’ Success. At Saarthee, we are passionate about guiding organizations towards insights fueled success. That’s why we call ourselves Saarthee–inspired by the Sanskrit word ‘Saarthi’, which means charioteer, trusted guide, or companion. Cofounded in 2015 by Mrinal Prasad and Shikha Miglani, Saarthee already encompasses all the components of Data Analytics consulting. Saarthee is based out of Philadelphia, USA with office in UK and India

Role and Responsibilities :

Develop, fine-tune, and deploy Large Language Models (LLMs) for various applications, including chatbots, virtual assistants, and enterprise AI solutions.

Build and optimize conversational AI solutions with at least 1 year of experience in chatbot development.

Implement and experiment with LLM agent development frameworks such as LangChain, LlamaIndex, AutoGen, and LangGraph .

Design and develop ML / DL-based models to enhance natural language understanding capabilities.

Work on retrieval-augmented generation (RAG) and vector databases (e.G., FAISS, Pinecone, Weaviate, ChromaDB) to enhance LLM-based applications.

Optimize and fine-tune transformer-based models such as GPT, LLaMA, Falcon, Mistral, Claude, etc., for domain-specific tasks.

Develop and implement prompt engineering techniques and fine-tuning strategies to improve LLM performance.

Work on AI agents, multi-agent systems, and tool-use optimization for real-world business applications.

Develop APIs and pipelines to integrate LLMs into enterprise applications.

Research and stay up-to-date with the latest advancements in LLM architectures, frameworks, and AI trends.

Requirements :

3-5 years of experience in Agentic AI, Machine Learning (ML), Deep Learning (DL), and NLP-based model development. Experience with Multi-modal AI models (text-to-image, text-to-video, speech synthesis, etc.).

Candidates having experience SDLC, Software Engineering will be preferred.

Hands-on experience in developing and deploying conversational AI / chatbots is Plus

Strong proficiency in Python and experience with ML / DL frameworks such as TensorFlow, PyTorch, and Hugging Face Transformers .

Experience with LLM agent development frameworks like LangChain, LlamaIndex, AutoGen, LangGraph .

Knowledge of vector databases (e.G., FAISS, Pinecone, Weaviate, ChromaDB) and embedding models .

Understanding of Prompt Engineering and Fine-tuning LLMs .

Familiarity with cloud services (AWS, GCP, Azure) for deploying LLMs at scale.

Experience in working with APIs, Docker, FastAPI for model deployment.

Strong analytical and problem-solving skills.

Ability to work independently and collaboratively in a fast-paced environment.