Emorphis Technologies - Senior Python AI/ML Engineer - LLM/RAG

Description :

Senior Python AI/ML Engineer

Experience : 4 to 8 Years

Location : Indore

(5 days Work from Office)

Key Responsibilities :

- Implement proof of concepts (POCs) in Engineering Systems and other innovation-driven domains where Machine Learning (ML) and Artificial Intelligence (AI) technologies can be applied.

- Design, develop, and implement ML/AI-based product features, including those leveraging Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks.

- Participate in coding, debugging, and solution delivery while adhering to coding and quality guidelines.

- Ensure high-quality, on-time delivery of product features and bug fixes aligned with customer and business requirements.

- Identify, design, and implement unit and integration tests to ensure quality, performance, and security standards are met.

- Manage the integration and version control of developed solutions using appropriate configuration management tools.

- Work collaboratively with cross-functional teams to build, train, and deploy LLM-based systems, ensuring scalability and reliability.

- Utilize off-the-shelf LLM services such as Azure OpenAI, OpenAI API, or Anthropic Claude, for integrating language understanding, reasoning, and generative capabilities into applications.

- Develop and fine-tune custom LLMs and implement RAG pipelines for context-aware conversational or generative AI solutions.

- Stay up to date with advancements in Agentic AI, including building autonomous AI agents capable of reasoning, planning, and tool integration experience in this area will be a strong advantage.

Required Skills & Experience :

- Strong programming proficiency in Python (scripting and object-oriented).

- Proven experience with Deep Learning and Machine Learning algorithms.

- Hands-on experience with frameworks such as TensorFlow, PyTorch, Keras, Scikit-learn, Caffe, Pandas, NumPy, Matplotlib.

- Solid understanding of Natural Language Processing (NLP), Deep Learning architectures, and Generative AI concepts.

- Practical experience in LLM fine-tuning, prompt engineering, and RAG model implementation.

- Familiarity with Agentic AI frameworks (e.g., LangChain, LlamaIndex, AutoGPT, or CrewAI) is highly desirable.

- Strong understanding of Software Design & Development principles, including OOPS/OOAD methodologies.

- Exposure to cloud-based AI services (Azure, AWS, GCP) and MLOps best practices is a plus.