AiSensy - Artificial Intelligence Engineer - LLM/RAG

About AiSensy :

AiSensy is a WhatsApp based Marketing & Engagement platform helping businesses like Adani, Delhi Transport Corporation, Yakult, Godrej, Aditya Birla Hindalco,

Wipro, Asian Paints, India Today Group Skullcandy, Vivo, Physicswallah, Cosco grow their revenues via 100,000+ Businesses with WhatsApp Engagement & Marketing 400Crores + WhatsApp Messages done between Businesses and Users via AiSensy per year.

Working with top brands like Delhi Transport Corporation, Vivo, Physicswallah & more.

High Impact as Businesses drive 25-80% Revenues using AiSensy and Growth Stage Startup backed by Marsshot.vc, Bluelotus.vc & 50+ Angel the Role :

We are seeking a highly skilled and innovative AI/ML Engineer to join our dynamic team.

In this role, you will design, develop, and deploy cutting-edge artificial intelligence (AI) solutions, leveraging advanced machine learning (ML) techniques and AI frameworks to address complex business challenges.

You will work closely with cross-functional teams to build intelligent systems and drive innovation, with a focus on implementing and optimizing modern AI technologies such as Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI Agents.

Key Responsibilities :

AI Model Development :

- Design, develop, and optimize AI solutions, including LLMs, RAG architectures, and Graph-based RAG systems, tailored to specific business needs.

- Develop and fine-tune models for tasks such as Natural Language Processing (NLP), Computer Vision, and Reinforcement Learning (RL).

Prompt Engineering and AI Agents :

- Work with prompt optimization to enhance LLM-based responses for specific use cases.

- Develop autonomous AI agents capable of completing multi-step tasks with minimal human Processing and Management :

- Collect, clean, preprocess, and organize datasets for effective AI and ML model training and evaluation.

- Leverage graph databases and vector stores for efficient data retrieval in AI-driven Selection and Optimization :

- Choose and implement appropriate algorithms, considering constraints such as scalability, interpretability, and real-time deployment requirements.

- Conduct hyperparameter tuning and optimization experiments to maximize model efficiency and and Integration :

- Deploy AI/ML models in production-grade environments, ensuring scalability, reliability, and seamless integration with existing systems.

- Implement model monitoring pipelines to ensure performance consistency over time.

Research and Development :

- Stay abreast of the latest trends and advancements in AI and ML technologies, such as transformer architectures, diffusion models, and multi-modal AI.

- Experiment with emerging tools like LangChain, Hugging Face, and OpenAI APIs to innovate and Knowledge Sharing :

- Work closely with data scientists, software engineers, and product managers to define project requirements and deliver impactful AI solutions.

- Document workflows, processes, and findings to enable knowledge sharing and continuity across Qualifications :

- Bachelors or Masters degree in Computer Science, AI, Data Science, Engineering, Mathematics, or a related :

- Minimum 3+ years in AI/ML roles with a proven track record in building and deploying AI-driven Proficiency :

- Proficiency in Python and AI/ML frameworks like TensorFlow, PyTorch, scikit-learn, or Keras.

- Experience working with LLMs, transformers, and generative AI tools.

- Familiarity with cloud platforms such as AWS, Google Cloud, or Azure, including AI-focused services like SageMaker and Vertex AI.

- Knowledge of vector databases (e.g., Pinecone, Milvus, Weaviate) and graph databases for RAG Expertise :

- Strong understanding of advanced statistical methods, mathematical concepts, and probabilistic models.

- Ability to analyze and interpret data for actionable insights and model Skills :

- Exceptional problem-solving and critical-thinking abilities.

- Strong communication skills to effectively collaborate with cross-functional teams.

- Adaptability to a fast-paced, innovation-driven Qualifications :

- Hands-on experience with LangChain, Hugging Face Transformers, or OpenAI API integrations.

- Expertise in specialized AI domains like multi-modal learning, conversational AI, and prompt engineering.

- Contributions to open-source AI projects or publications in recognized AI/ML conferences or journals.

- Familiarity with deploying AI Agents in production systems.