We are seeking a skilled AI Engineer with 2-4 years of experience to design, develop, and deploy AI/ML solutions, with a strong emphasis on Generative AI, NLP, Retrieval-Augmented Generation (RAG), and Time Series Forecasting. The ideal candidate will have hands-on experience with LangGraph and other Generative AI frameworks to build cutting-edge AI applications.
Key Responsibilities:
- Develop and deploy AI/ML models with a focus on NLP, Generative AI, RAG, and Time Series Forecasting workflows.
- Engineer and refine prompts to optimize performance for large language models (LLMs) and generative AI applications.
- Implement and maintain data preprocessing pipelines, including data cleansing, feature engineering, embedding generation, and transformation for time series data.
- Develop end-to-end solutions integrating LLMs with VectorDB (e.g., Weaviate, Pinecone, FAISS) for document retrieval, semantic search, and contextual query answering.
- Utilize LangGraph and other Generative AI frameworks to build structured workflows for LLM-based applications.
- Train and fine-tune machine learning models, including LLMs, to optimize performance for various use cases.
- Analyze and interpret complex datasets, including time series data, ensuring scalable and efficient AI model deployment.
- Collaborate with cross-functional teams to integrate AI/ML models into existing systems and workflows.
- Ensure models are robust, scalable, and adhere to best practices in ethical AI development.
- Conduct testing, performance benchmarking, and iterative refinements of AI models and pipelines.
- Stay updated with the latest advancements in AI/ML, NLP, and cloud technologies and recommend integration strategies for emerging tools and techniques.
- Create technical documentation and presentations to effectively communicate AI concepts to stakeholders.
Key Skills and Qualifications:
Required Skills:
-
AI/ML Expertise:
Proven experience in developing, fine-tuning, and deploying AI/ML models, focusing on NLP, Generative AI, and Time Series Forecasting. -
Prompt Engineering:
Proficiency in designing, testing, and optimizing prompts for LLMs. -
Data Analysis:
Strong ability to process and interpret large and complex datasets, including time series data, for AI model training and validation. -
Programming:
Proficiency in Python and experience with AI/ML frameworks like TensorFlow, PyTorch, and scikit-learn. -
NLP Techniques:
Understanding of tokenization, embeddings, transformer-based models (e.g., BERT, GPT, LLaMA), and RAG workflows. -
Vector Databases:
Experience with Weaviate, Pinecone, FAISS, or similar VectorDBs for document retrieval and storage. -
LangGraph & GenAI Frameworks:
Hands-on experience with LangGraph, LangChain, HuggingFace Transformers, OpenAI API, and other Generative AI tools. -
Cloud Deployment:
Familiarity with deploying AI solutions on AWS, GCP, or Azure. -
Time Series Forecasting:
Experience with ARIMA, LSTM, Prophet, and other forecasting techniques. -
Model Training & Fine-Tuning:
Ability to train and fine-tune machine learning models, including large language models (LLMs), to enhance performance and accuracy. -
Problem-Solving & Collaboration:
Strong analytical, problem-solving, and teamwork skills to work effectively in a cross-functional environment.
Preferred Skills:
- Experience in implementing RAG workflows and integrating generative AI with retrieval-based systems.
- Familiarity with ethical AI principles and compliance frameworks.
- Knowledge of additional programming languages such as JavaScript or SQL.
- Proficiency in MLOps practices for automating AI/ML pipelines and lifecycle management.
- Experience in developing AI-driven applications for real-world industry use cases.