Machine Learning Engineer, Agentic Marketing
Adobe · Bengaluru · Posted 2026-07-28
Tech stack: Python
Apply on the company site · Get a referral for this role
Adobe salary & ratings · Adobe interview process · More live openings
About the role
The Opportunity Join Adobe as a Machine Learning Engineer on the Agentic Marketing team. You will help build AI agents that simplify the marketing supply chain from campaign brief to launch. You will join a senior team, make core technical decisions, and deliver solutions quickly to customers. This role offers the chance to work with world-class professionals and lead major systems from conception to production. What you'll do Develop and build production agent systems on top of large language models, including planning, tool use and function calling, and long-running tasks that move marketing work through the pipeline. Own a core part of the agent stack from the first version to production. This could include orchestration and planning, the tool and function-calling layer, agent memory and state, or retrieval over brand and asset data. Build evaluation and reliability systems to ensure agent functionality, covering task success, grounding, regression checks, and brand-safety and compliance guardrails. Make architecture and build-versus-buy decisions, raising the engineering bar on the team. Collaborate closely with product, build, and research to turn current agent research into shipped features. Mentor other engineers, setting the standard for code quality and speed. What you need to succeed Several years of engineering experience, typically five or more, with recent hands-on work building and shipping LLM-based applications in production. Experience crafting agentic systems on LLMs, including multi-step planning, tool and function calling, orchestration, and long-running tasks. Strong software engineering fundamentals in Python, data structures, algorithms, distributed systems, and API composition, with a history of building software quickly and well. Experience building evaluation systems for software that does not behave deterministically, and a clear sense of which metrics actually matter. Owning a system means managing it from initial release to live deployment. Experience at a startup or similar environment is preferred. Comfort working with ambiguity at a fast pace, and good product judgment. Nice to have Experience with agent and orchestration frameworks such as LangGraph, and common LLM tooling such as vLLM, Hugging Face, and Weights & Biases. Fine-tuning or post-training experience (SFT, DPO, GRPO) applied to tool use or agent behavior. Experience in marketing, creative, or content technology, or with workflow-automation products. Open-source contributions. An MS or PhD in Computer Science, Machine Learning, or a related field, or equivalent experience.
Qualifications
- Several years of engineering experience, typically five or more, with recent hands-on work building and shipping LLM-based applications in production.
- Experience crafting agentic systems on LLMs, including multi-step planning, tool and function calling, orchestration, and long-running tasks.
- Strong software engineering fundamentals in Python, data structures, algorithms, distributed systems, and API composition, with a history of building software quickly and well.
- Experience building evaluation systems for software that does not behave deterministically, and a clear sense of which metrics actually matter.
- Owning a system means managing it from initial release to live deployment.
- Experience at a startup or similar environment is preferred.
- Comfort working with ambiguity at a fast pace, and good product judgment.
- Nice to have
- Experience with agent and orchestration frameworks such as LangGraph, and common LLM tooling such as vLLM, Hugging Face, and Weights & Biases.
- Fine-tuning or post-training experience (SFT, DPO, GRPO) applied to tool use or agent behavior.
- Experience in marketing, creative, or content technology, or with workflow-automation products.
- Open-source contributions.
- An MS or PhD in Computer Science, Machine Learning, or a related field, or equivalent experience.
Responsibilities
- Develop and build production agent systems on top of large language models, including planning, tool use and function calling, and long-running tasks that move marketing work through the pipeline.
- Own a core part of the agent stack from the first version to production.
- This could include orchestration and planning, the tool and function-calling layer, agent memory and state, or retrieval over brand and asset data.
- Build evaluation and reliability systems to ensure agent functionality, covering task success, grounding, regression checks, and brand-safety and compliance guardrails.
- Make architecture and build-versus-buy decisions, raising the engineering bar on the team.
- Collaborate closely with product, build, and research to turn current agent research into shipped features.
- Mentor other engineers, setting the standard for code quality and speed.