P

PubMatic

SSP for publishers, optimizes ad revenue

Senior Software Engineer - Agentic AI

AI Application EngineeringUpdated on Nov 18
Full-timePune, Maharashtra, IndiaNo salary listed

About the Job

Requirements

  • 2 to 5 years of total experience and a strong understanding of large language models and their underlying principles, including transformer architecture, attention mechanisms, and hyperparameter tuning.
  • Proven experience designing and building AI agents, including multi-agent orchestration, tool-use patterns, multi-step planning, and short-term and long-term agent memory architectures.
  • Hands-on experience with agentic frameworks such as LangGraph, CrewAI, or AutoGen, and familiarity with retrieval-augmented generation pipelines integrating external knowledge sources such as documents, databases, and APIs.
  • In-depth knowledge of vector databases and indexing algorithms, with practical experience using FAISS, Pinecone, Weaviate, or Milvus.
  • Experience with agent observability, tracing, and guardrails using tools such as Langfuse or equivalent tools to support reliability, safety, and debuggability of agentic systems.
  • Proficiency in prompt engineering, including crafting, iterating, and optimizing complex prompts for context-sensitive, domain-specific large language model outputs.
  • 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.
  • A bachelor's degree in engineering or an equivalent degree from a well-known institute or university.

Responsibilities

  • Provide technical leadership and mentorship to engineering teams while collaborating with architects, product managers, and UX designers to create AI solutions addressing complex customer challenges.
  • Lead the design, development, and deployment of AI-driven features, owning work end-to-end from feasibility analysis and design specifications through execution and release, and iterating based on customer feedback in an Agile environment.
  • Lead technical design meetings and produce detailed design documents outlining scalable, secure, and robust AI architectures.
  • Ensure solutions align with long-term product strategy and technical roadmaps.
  • Implement and optimize large language models for specific use cases, including fine-tuning models, deploying pre-trained models, and evaluating performance.
  • Develop AI agents powered by retrieval-augmented generation systems, integrating external knowledge sources to improve generated content accuracy and relevance.
  • Design, implement, and optimize vector databases for efficient and scalable vector search, and work on vector indexing algorithms.
  • Create and fine-tune prompts to improve large language model performance in generating precise, contextually relevant responses.
  • Use evaluation frameworks and metrics such as Evals to assess and improve generative model and AI system performance.
  • Work with data scientists, engineers, and product teams to integrate AI-driven capabilities into customer-facing products and internal tools.
  • Stay current with research and trends in large language models, retrieval-augmented generation, and generative AI technologies.
  • Continuously monitor and optimize models to improve performance, scalability, and cost efficiency.

Desired Qualifications

  • Experience building AI agents using graph-based architectures, including knowledge graph embeddings and graph neural networks.
  • Experience training small base models using custom data, including data collection, preprocessing, and fine-tuning models for specific domains or tasks.
  • Familiarity with deploying AI models on cloud platforms such as AWS, GCP, or Azure, and with containerization technologies such as Docker and Kubernetes.
  • Familiarity with programmatic advertising, real-time bidding, or ad auction mechanics.
  • Knowledge of Model Context Protocol or similar tool-integration standards.
  • Publication or contributions to research in AI, large language models, or related fields.
  • Ability to present complex technical ideas and results to technical and non-technical stakeholders.

About the Company

PubMatic

SSP for publishers, optimizes ad revenue

PubMatic provides a digital advertising platform that helps publishers boost revenue from websites and apps through a Supply-Side Platform (SSP). The SSP lists ad space, connects publishers with advertisers, and uses real-time bidding to award impressions to the highest bidder. The company earns a commission on successful ad placements and offers analytics, audience targeting, identity solutions, and support for video and CTV ads. Its goal is to help publishers maximize ad revenue by efficiently monetizing inventory and improving reach.

Company size
1,001-5,000
Company stage
IPO
Headquarters
Redwood City, CA
Founded
2006

Recently Posted Jobs

Explore more opportunities at PubMatic

See more jobs