Confirmed on the employer's own hiring board on Nov 16, 2026. First seen by Alion on Nov 16, 2026.
About Ovative Group:
Ovative Group is an independent, full-funnel media, measurement, and creative firm transforming how brands grow. We partner with leading names like American Eagle, Best Buy, Domino’s, The Home Depot, Polaris, and UnitedHealth Group to build smarter media and measurement programs that drive real, profitable growth.
We don’t just track performance-we redefine it. Powered by our proprietary intelligence platform, EMRge, and our holistic metric Enterprise Marketing Return (EMR), we help brands connect revenue, customer, and brand outcomes into one clear picture of success. Our approach to full-funnel strategy, buying, and measurement delivers results that matter-and it’s getting noticed. Our work has been recognized by Digiday, Google, USA Today, Inc. 5000, and Search Engine Land.
About the team:
The AI OS & Agentic Execution team builds agents that do real operational work at Ovative: agents that plan multistep tasks, use tools across the systems our teams rely on, check their own output, and bring people in at the right moments. Every agent we ship runs on a shared, governed foundation, so each new agent builds on the last instead of starting over.
This is an individual contributor role where you'll partner closely and take technical direction from another Lead AI Engineer on our team. You will work closely with our Lead AI Engineer as a technical leader on the team, mentor other engineers, and partner with Platform Engineering, Information Security, and the media operators who will use what we build.
About the role:
We are hiring a Lead AI Engineer to lead the design, build, and operation of agents and agentic workflows in production. You will own agents end to end, starting from a loosely defined business problem and finishing with a system that runs reliably, is measured, and is trusted by the people who depend on it.
You will set the technical direction for the agents you lead: when a problem calls for an autonomous agent, a structured agentic workflow, or plain code; how tools and context are designed; and how quality is proven before anything touches a live client account. You will turn those decisions into patterns, reference implementations, and standards the rest of the team builds on.
You will own major pieces of the shared foundation every agent runs on, and design them so a new agent, or an existing agent extended to a new platform, reuses what is already there. We are looking for someone who has led agent systems into production, owned them through failures and change, and helped other engineers do the same.
Responsibilities of a Lead AI Engineer:
Lead agent design and delivery
- Own agents end to end: scope the problem with operators and the product owner, set the technical design, break the work into milestones, and lead the build through launch and beyond
- Make the core architecture calls for each agent: level of autonomy, agent loop design, single agent versus multi agent orchestration, stopping conditions, escalation paths, and where deterministic code must own a step
- Design agents and their tools so they extend to new platforms and use cases without a rebuild
- Lead design reviews and code reviews for agent work, holding a high bar for tool design, context engineering, state management, and failure handling
- Choose models for each task based on quality, latency, and cost, and tune agents to meet targets on all three
Own the shared foundation
- Own the design and roadmap for major foundation components such as action checks at the gateway, identity and client level access, durable state for pause and resume, audit logging, and the kill switch
- Shape how approved tools are exposed through MCP servers with scoped credentials, and lead technical work on the agent registry and observability layer
- Bring a clear point of view to build versus buy decisions for foundation capabilities, grounded in cost, risk, and fit with our stack
- Define the security model for agents that take action in client accounts, including least privilege access, protection against prompt injection and unsafe tool use, and approval rules for high impact actions
Set the quality bar
- Define the evaluation framework the team uses for agent behavior: task success, tool selection, trajectory quality, safety, and regression testing in a sandbox before release
- Set standards for tracing, metrics, and cost tracking so we can see what any agent did at every step, why, how long it took, and what it cost
- Own production health for the agents you lead: run incident response, write post incident reviews, and turn every failure into an evaluation case, a guardrail, or a design change
Raise the team
- Mentor engineers through pairing, design feedback, and code review, and help them grow into owning agents themselves
- Create reference implementations, templates, and documentation that make the next agent faster and safer to build
- Partner with the Lead AI Engineer on the technical roadmap, sequencing, and estimates, and lead technical discussions with partner teams when needed
Work with people
- Sit with the operators whose work an agent will take on, map how the process really runs, and shape the agent and its human checkpoints around it
- Represent the team in architecture and security reviews with Information Security and Platform Engineering, and help shape shared standards for MCP policies, logging, environments, Databricks, and Lakebase
- Explain tradeoffs, risks, and progress clearly to operators, product partners, and leaders
Requirements:
We care most about what you have led, built, and run. The strongest candidates will have owned agent systems that take action in real systems from first design through life in production, and will have made the engineers around them better.
- 7+ years of software engineering experience, with backend or platform work as a core part of it, with 2+ years building LLM based systems in production. Has owned architecture decisions for agentic systems, including evaluation, observability, and deployment.
- You have led the technical design and delivery of multiple autonomous agents or agentic systems in production that took actions through tools or APIs, and you can walk us through the architecture decisions, what broke, and how you changed the design
- You have owned shared infrastructure or platform components that other engineers or agents built on, and can explain how you designed them for reuse
- Deep experience with tool calling and agent orchestration through MCP, an agent SDK such as the Claude Agent SDK or OpenAI Agents SDK, or a framework such as LangGraph, plus strong judgment on when a framework helps and when plain code is better
- Proven skill in tool design and context engineering for long running tasks: prompt structure, retrieval, memory, and keeping agents from drifting
- Experience designing multi agent systems, including handoffs, shared state, and debugging failures that span agents
- You have built or defined an evaluation framework that a team adopted, and used it to make release decisions
- You have led incident response for a production AI system and can describe how you found the root cause using traces and logs
- Experience securing agents that write to external systems: least privilege access, credential scoping, prompt injection defenses, and audit trails
- Experience managing cost and latency for LLM systems at production volume
- Strong Python, SQL, and Postgres, and deep experience building backend services with authentication, authorization, and least privilege access
- Experience integrating with third party APIs that write data, including retries, idempotency, rate limits, and safe rollback
- Experience with at least one major cloud (AWS, GCP, or Azure), containers, and CI/CD, including setting up environments and deployment paths others use
- A track record of mentoring engineers and leading technical decisions across teams
- You can explain a technical tradeoff to an operator, an engineer, or a senior leader with equal clarity
Nice to have:
- Experience with the Claude API, the Claude Agent SDK, or Claude Enterprise
- Experience designing or running an AI or MCP gateway, policy enforcement for agents, or agent registries
- Databricks experience, including Lakebase or Unity Catalog
- Experience with ad platform APIs such as the Meta Marketing API or Google Campaign Manager 360, or with ClickUp and similar work management APIs
- Experience leading AI systems through security or compliance reviews in governed environments, including SOC 2
- Experience as a founding or early engineer on an AI platform team
- Background in marketing, media, or professional services
Pay Transparency:
At Ovative, we offer a transparent view into three core components of the total compensation package: Base Salary, Annual Bonus, and Benefits.
For our Sr. Manager positions, including the position of Lead AI Engineer, our compensation range is from $125,000 to $175,000 on an annualized basis, which is inclusive of an annual bonus opportunityof up to 25% of base salary
Working at Ovative Group:
We provide strong, competitive, holistic benefits that understand the importance of your life inside and out of work.
At Ovative, culture isn’t a buzzword-it’s the reason we’ve been named a Top Workplace for ten years running. We lead with trust, transparency, and a commitment to doing the hard work others avoid.
We offer flexibility. You'll work from our Minneapolis, Chicago, or New York office on set days each week, and an option to work remote on others.
Our open floor plan reflects our open communication and flat structure-where interns collaborate with VPs, analysts partner with senior leaders, and our CEO engages with every team member. Together, we create an environment where smart, driven people can do their best work and support one another in the process.
We’re equally committed to inclusion and belonging. Ovative fosters a workplace where everyone can participate and thrive-regardless of ethnicity, gender, sexual orientation, gender identity, or expression or other protected class status. Our benefits and policies reflect that commitment, from inclusive medical leave coverage for same-sex spouses to equitable care and support for all families.
Benefits:
We strive to hire and retain the best talent by offering fair, competitive compensation, a meaningful bonus program, and excellent health coverage. When the company performs well, we all benefit.
Some tangible benefits and amenities we enjoy:
- Access to all office spaces in MSP, NYC, and CHI
- Frequent, paid travel to our Minneapolis headquarters for company events, team events, and in-person collaboration with teams
- Generous paid vacation policy
- 401k match program
- Top-notch health insurance options, inclusive of same sex partners
- Family formation benefits including reimbursement options for fertility, pregnancy, and parenting needs
- Monthly stipend for your mobile phone and data plan
- Sabbatical program
- Charitable giving via our time and a financial match program
- Shenanigan’s Day
Additional information can be found at Ovative's Career Page.
The details of the benefits are covered by applicable plan documents for group benefits and by company policies where a plan document does not apply.
Working at Ovative won’t be easy-but if you like challenging, hard work, driving results, and being surrounded by the best talent, it has the potential to be the most rewarding job you’ll ever have. If you think you can make us better, we want to hear from you!
EEO & Accessibility:
Ovative is an Equal Opportunity Employer committed to a respectful, inclusive workplace for all. Applicants receive consideration without regard to legally protected characteristics (e.g., color, religion, creed, national origin, sex, pregnancy, childbirth and related conditions, sexual orientation, gender identity/, gender expression, gender identity, age, physical or mental disability, marital/ status, familial status, military or veteran’s status, genetic information, status with regard to public assistance, and any other status protected under applicable law).
We provide reasonable accommodations consistent with the Americans with Disabilities Act and applicable state law to qualified applicants and employees with disability, unless doing so would create an undue hardship.
If you need assistance or accommodation at any stage of the application or interview process due to a disability, please contact us at [email protected].
Application Details and Process:
Applicants must be legally authorized to work in the United States for any employer on a full-time basis, without current or future need for visa sponsorship. Ovative is unable to sponsor or take over sponsorship of an employment visa for this position. In compliance with federal law, all persons hired will be required to verify identity and eligibility to work in the United States and to complete the required employment eligibility verification documentation upon hire.
Open Until Filled or Otherwise Withdrawn:
We encourage interested candidates to apply early. The position will remain open for at least 10 business days from the first day of posting. After this time, if the position has not been filled, the posting will remain open until the position is filled, or until the posting is otherwise closed or withdrawn for business reasons.

