SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 240,000 - 240,000 / annual
Zeta Global (NYSE: ZETA) is an AI-powered marketing cloud that uses advanced artificial intelligence and consumer data to help marketers acquire, grow, and retain customers. The company's Zeta Marketing Platform unifies identity, intelligence, and omnichannel activation into a single platform powered by one of the industry's largest proprietary databases and AI.
You will drive the design and development of the next generation of agentic, reliable, and scalable GenAI platforms supporting state-of-the-art large language models, evaluation systems, and secure developer tooling. This is a high-impact technical leadership role where you will shape architectural direction and ensure excellence across multiple critical systems.
Key responsibilities include:
- Lead the design and development of secure, scalable platform services and tooling for LLM-powered applications, agentic workflows, and experimentation frameworks
- Design and implement retrieval and knowledge systems (RAG pipelines, embeddings, vector stores) to support enterprise use cases
- Establish evaluation frameworks, benchmarks, and feedback loops to measure and continuously improve quality, correctness, and safety of GenAI systems
- Build observability and debugging capabilities for LLM applications, including tracing, cost monitoring, latency analysis, and failure detection
- Optimize cost and performance of GenAI workloads through model routing, caching, prompt optimization, and efficient infrastructure design
- Architect multi-tenant capabilities including isolation, configuration, quota management, and cost attribution
- Implement GenAI-specific security controls, including prompt injection mitigation, data protection, and access governance
- Design and implement agent orchestration frameworks, including tool integration, state management, and workflow control
- Build developer-facing APIs, SDKs, and tooling to enable rapid experimentation and productionization of GenAI use cases
- Drive end-to-end lifecycle management from experimentation to production, including versioning, deployment strategies, and rollback mechanisms
- Integrate and evaluate multiple model providers and frameworks, defining abstraction and selection strategies
The role offers hybrid flexibility with the option to telecommute 3 days per week.
REQUIREMENTS:
- Bachelor's degree in Computer Science, Computer Engineering, Software Engineering, or Information Systems
- 5+ years of experience in software engineering or related occupation
- Experience with generative AI, large language models (LLMs), and cloud infrastructure
- Proficiency in one or more of: C#, Java, JavaScript, Go, or Python
- Experience with GenAI platform technologies (MCP, LangGraph, OpenAI, Bedrock)
