Principal Agentic AI Engineer

Zeta Global

Be an Early ApplicantFull Timeprincipal

San Francisco, California, United StatesPosted Today

Resume Keywords to Include

Make sure these keywords appear in your resume to improve ATS scoring

PythonJavaGoAWSMicroservices

Job Description

WHO WE ARE  Zeta Global (NYSE: ZETA) is the AI-Powered Marketing Cloud that leverages advanced artificial intelligence (AI) and trillions of consumer signals to make it easier for marketers to acquire, grow, and retain customers more efficiently. Through the Zeta Marketing Platform (ZMP), our vision is to make sophisticated marketing simple by unifying identity, intelligence, and omnichannel activation into a single platform – powered by one of the industry’s largest proprietary databases and AI. Our enterprise customers across multiple verticals are empowered to personalize experiences with consumers at an individual level across every channel, delivering better results for marketing programs. Zeta was founded in 2007 by David A. Steinberg and John Sculley and is headquartered in New York City with offices around the world. To learn more, go to <a href="https://www.zetaglobal.com">www.zetaglobal.com</a>. Role Snapshot  We’re hiring a hands-on Agentic AI engineer to build bidder-adjacent agents that improve campaign performance using RAG + tool-using workflows in a closed-loop ACE (Observe → Reason → Act → Evaluate). This is not a classic “train a model and deploy it” role—this is agentic decisioning + evaluation + safety in a low-latency AdTech environment.  What You’ll Do  <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="1" data-aria-level="1">Build bidder-adjacent agentic workflows that recommend/execute campaign control actions (targeting constraints, budget & pacing levers, bid modifiers, supply/inventory selection, creative routing). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="2" data-aria-level="1">Implement production-grade RAG: retrieval from policies/playbooks, campaign history, aggregates, and near-real-time telemetry; optimize grounding and reduce hallucinations. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="3" data-aria-level="1">Create safe tool/action interfaces: idempotent execution, audit logs, dry-run + approval gates, rate limits, rollback/fallback behaviors. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="4" data-aria-level="1">Own AgentOps: eval harnesses, regression suites, online experimentation (A/B), metrics tied to outcomes (CPA/ROAS, pacing, quality, margin). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="5" data-aria-level="1">Add observability end-to-end (tracing prompts/retrieval/tool calls/latency) and reliability patterns (timeouts, circuit breakers, safe defaults). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="6" data-aria-level="1">Partner with Backend/Bidding, Data Platform, DS/Optimization, Product, and SRE to define the boundary between deterministic per-request bidding and agent-driven control-plane decisions. </li> </ul> Must-Have Qualifications  <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="7" data-aria-level="1">10+ years building production backend and/or applied AI systems (design → ship → operate). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="8" data-aria-level="1">Strong engineering in Java or Go (Python OK for evals/tooling). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="9" data-aria-level="1">Hands-on experience with LLMs and agentic patterns (tool use, structured outputs, multi-step loops). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="10" data-aria-level="1">Hands-on RAG experience (embeddings, hybrid retrieval, reranking, chunking, context assembly). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="11" data-aria-level="1">Experience building evals and monitoring for AI systems (offline benchmarks + online experiments). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="12" data-aria-level="1">Cloud + distributed systems fundamentals (APIs, microservices, streaming/eventing; AWS preferred). </li> </ul> Nice-to-Have  <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="13" data-aria-level="1">Programmatic advertising (DSP/SSP/RTB) or other high-scale real-time decisioning domains. </li> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="13" data-aria-level="1">Experience with safety/policy enforcement for agent tools (prompt/tool sanitization, allowlists, schema validation). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="15" data-aria-level="1">Experience designing “AI control plane” systems that influence production outcomes while keeping serving paths stable. </li> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":360,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"singleLevel"}" data-aria-posinset="16" data-aria-level="1">Familiarity with experimentation platforms, feature stores, and large-scale telemetry pipelines. </li> </ul> BENEFITS & PERKS <ul> <li>Unlimited PTO</li> <li>Excellent medical, dental, and vision coverage</li> <li>Employee Equity</li> <li>Employee Discounts, Virtual Wellness Classes, and Pet Insurance And more!!</li> </ul> SALARY RANGE The salary range for this role is $220,000 - $250,000, depending on location and experience.  PEOPLE & CULTURE AT ZETA Zeta considers applicants for employment without regard to, and does not discriminate on the basis of an individual’s sex, race, color, religion, age, disability, status as a veteran, or national or ethnic origin; nor does Zeta discriminate on the basis of sexual orientation, gender identity or expression.   We’re committed to building a workplace culture of trust and belonging, so everyone feels invited to bring their whole selves to work. We provide a forum for employees to celebrate, support and advocate for one another. Learn more about our commitment to diversity, equity and inclusion here:  <a id="menur45rm" class="fui-Link ___1q1shib f2hkw1w f3rmtva f1ewtqcl fyind8e f1k6fduh f1w7gpdv fk6fouc fjoy568 figsok6 f1s184ao f1mk8lai fnbmjn9 f1o700av f13mvf36 f1cmlufx f9n3di6 f1ids18y f1tx3yz7 f1deo86v f1eh06m1 f1iescvh fhgqx19 f1olyrje f1p93eir f1nev41a f1h8hb77 f1lqvz6u f10aw75t fsle3fq f17ae5zn" href="https://zetaglobal.com/blog/a-look-into-zetas-ergs/" target="_blank">https://zetaglobal.com/blog/a-look-into-zetas-ergs/</a>  ZETA IN THE NEWS! <a href="https://zetaglobal.com/press/?cat=press-releases">https://zetaglobal.com/press/?cat=press-releases</a>  #LI-YW1