Lead Software Engineer(Platform / GenAI)

Lead Software Engineer We're looking for a Lead Software Engineer to help shape the future of Ad Technology's Generative AI platform, focusing on building reusable capabilities and intelligent agents that streamline operational workflows. This is a unique opportunity to apply cutting-edge AI tools to real-world challenges, improve efficiency, reduce manual effort, and empower teams across our ad delivery ecosystem. Responsibilities: Design and build reusable GenAI platform components, including prompt orchestration layers, secure gateway abstraction using tools like LiteLLM, Portkey, or Kong, embedding and retrieval infrastructure with vector databases like Pinecone or FAISS, and audit, logging, trace analysis with tools like LangSmith. Implement guardrails for output validation, safety checks, and policy enforcement. Develop multi-turn LLM agents and tools using LangGraph and LangChain to automate operational workflows. Build APIs, SDKs, and accelerator components for internal product teams, bots, and platforms to rapidly adopt GenAI services. Standardize approaches to context management, tool calling, fallback handling, and observability across agents. Ensure platform components meet security, governance, and compliance standards. Collaborate with infrastructure, data, security, and product teams to integrate GenAI workflows into existing systems. We are committed to creating inclusive environments where everyone can bring their full, authentic selves to work. We are an equal opportunity employer that values diversity and inclusion. Qualified candidates will be considered without regard to race, religion, sex, age, marital status, national origin, sexual orientation, citizenship status, disability, or other protected characteristics. Skills and requirements: 8+ years of backend or platform engineering experience, with a proven track record of building scalable APIs. Hands-on experience integrating with LLM APIs such as OpenAI, Claude, and Anthropic, and building LLM-powered workflows, agents, or AI assistants. Proficiency in Python; familiarity with LangChain, LangGraph, or similar LLM orchestration frameworks. Knowledge of observability practices for LLM systems, including logging, latency tracking, and output monitoring. Experience with LLM evaluation and testing frameworks to validate prompt behavior and agent reliability. Strong understanding of cloud-native design, secure AI API integration, and service scalability. Experience with vector databases like Pinecone, FAISS, or Weaviate, and retrieval-augmented generation (RAG) techniques. Ability to build modular, reusable GenAI components for cross-functional adoption. Experience working with CI/CD pipelines and collaborating with DevOps teams. Familiarity with tools like LangSmith, PromptLayer, or tracing tools for debugging LLM workflows. Knowledge of AI gateway patterns and usage throttling with Kong, LiteLLM, or Portkey.ai. Understanding of guardrails, safety evaluations, prompt injection defense, and model governance frameworks. Previous experience building platforms or enablement tooling used across multiple engineering teams. Exposure to infrastructure or DevOps automation is a plus. This role is ideal for engineers excited to work at the intersection of backend systems, AI orchestration, platform architecture, and enterprise automation. Join our collaborative team at the forefront of GenAI enablement and help shape how modern AI tools are applied to operational challenges in a leading ad tech environment.

#J-18808-Ljbffr