Software Engineer, AI-Powered Advertising Agents

Role Overview: As an engineer at PubMatic, your main responsibility will be to specialize in Generative AI and AI agent development. You will play a crucial role in building and optimizing advanced AI agents that utilize technologies such as Retrieval-Augmented Generation (RAG), vector databases, and large language models (LLMs). Your work will involve enhancing Generative AI capabilities to handle complex information retrieval, contextual generation, and adaptive interactions. Key Responsibilities: - Collaborate with engineers, architects, product managers, and UX designers to create innovative AI solutions for new customer use-cases. - Independently work and iterate based on customer feedback to make necessary product tweaks. - Implement and optimize large language models (LLMs) for specific use cases through fine-tuning, deploying pre-trained models, and evaluating performance. - Develop AI agents powered by RAG systems, integrating external knowledge sources to enhance the accuracy and relevance of generated content. - Design, implement, and optimize vector databases (e.g., FAISS, Pinecone, Weaviate) for efficient and scalable vector search, and work on various vector indexing algorithms. - Create sophisticated prompts and fine-tune them to enhance the performance of LLMs in producing precise and contextually relevant responses. - Utilize evaluation frameworks and metrics (e.g., Evals) to assess and enhance the performance of generative models and AI systems. - Collaborate with data scientists, engineers, and product teams to integrate AI-driven capabilities into customer-facing products and internal tools. - Stay updated with the latest research and trends in LLMs, RAG, and generative AI technologies to drive innovation in the company's offerings. - Continuously monitor and optimize models to enhance their performance, scalability, and cost efficiency. Qualifications Required: - Strong understanding of large language models (e.g., GPT, BERT, T5) and their underlying principles, including transformer architecture and attention mechanisms. - Proven experience in building AI agents with Retrieval-Augmented Generation to enhance model performance using external data sources. - In-depth knowledge of vector databases, vector indexing algorithms, and experience with technologies like FAISS, Pinecone, Weaviate, or Milvus. - Ability to craft complex prompts to guide the output of LLMs for specific use cases, enhancing model understanding and contextuality. - Familiarity with Evals and other performance evaluation tools for measuring model quality, relevance, and efficiency. - Proficiency in Python and experience with machine learning libraries such as TensorFlow, PyTorch, and Hugging Face Transformers. - Experience with data preprocessing, vectorization, and handling large-scale datasets. - Ability to present complex technical ideas and results to both technical and non-technical stakeholders. Company Details: PubMatic is a leading digital advertising platform that offers transparent advertising solutions to publishers, media buyers, commerce companies, and data owners. The company was founded in 2006 with the vision that data-driven decision-making would be the future of digital advertising. PubMatic enables content creators to run a more profitable advertising business, allowing them to invest back into multi-screen and multi-format content that consumers demand. (Note: The "Additional Information" section has been omitted as it does not contain relevant job description details.),