Lead AI Engineer

Ovative Group•Minneapolis, MN
•Hybrid

About The Position

Ovative Group is hiring a Lead AI Engineer for its AI OS & Agentic Execution team, which builds production agents that plan multistep tasks, use tools across company systems, check their own output, and involve people at appropriate points. Agents run on a shared, governed foundation designed for reuse. This is an individual contributor role that partners closely with and takes technical direction from another Lead AI Engineer. The role also provides technical leadership, mentors engineers, and partners with Platform Engineering, Information Security, and media operators. The Lead AI Engineer will lead the design, delivery, and operation of agents and agentic workflows, owning them from loosely defined business problems through reliable, measured production use. The role sets technical direction for agent autonomy, workflows, tools, context, and quality assurance, and turns decisions into reusable patterns, reference implementations, and standards. It also owns major components of the shared agent foundation, including capabilities that support new agents and extensions to new platforms. The position is listed among Ovative's Sr. Manager positions for compensation purposes. The annualized compensation range is $125,000 to $175,000, inclusive of an annual bonus opportunity of up to 25% of base salary. The role may be based in the Minneapolis, Chicago, or New York office, with work from the office on set days each week and an option to work remotely on other days. Applicants must be authorized to work full time in the United States without current or future visa sponsorship.

Requirements

  • At least 7 years of software engineering experience, with backend or platform work as a core part of that experience, including at least 2 years building LLM-based systems in production.
  • Experience owning architecture decisions for agentic systems, including evaluation, observability, and deployment.
  • Experience leading the technical design and delivery of multiple autonomous agents or agentic systems in production that take actions through tools or APIs, and explaining their architecture, failures, and subsequent design changes.
  • Experience owning shared infrastructure or platform components used by other engineers or agents, with the ability to explain how they were designed for reuse.
  • Deep experience with tool calling and agent orchestration through MCP, an agent SDK such as Claude Agent SDK or OpenAI Agents SDK, or a framework such as LangGraph, and sound judgment about when to use a framework versus plain code.
  • Proven skill in tool design and context engineering for long-running tasks, including prompt structure, retrieval, memory, and preventing agent drift.
  • Experience designing multi-agent systems, including handoffs, shared state, and debugging failures across agents.
  • Experience building or defining an evaluation framework adopted by a team and using it to make release decisions.
  • Experience leading incident response for a production AI system and finding root causes using traces and logs.
  • Experience securing agents that write to external systems, including 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 skills, and deep experience building backend services with authentication, authorization, and least-privilege access.
  • Experience integrating with third-party APIs that write data, including handling retries, idempotency, rate limits, and safe rollback.
  • Experience with at least one major cloud provider (AWS, GCP, or Azure), containers, and CI/CD, including setting up environments and deployment paths used by others.
  • Track record of mentoring engineers and leading technical decisions across teams.
  • Ability to explain technical tradeoffs clearly to operators, engineers, and senior leaders.
  • 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.

Nice To Haves

  • Experience with the Claude API, Claude Agent SDK, or Claude Enterprise.
  • Experience designing or operating an AI or MCP gateway, agent policy enforcement, or agent registries.
  • Databricks experience, including Lakebase or Unity Catalog.
  • Experience with advertising platform APIs such as Meta Marketing API or Google Campaign Manager 360, or work management APIs such as ClickUp.
  • 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.

Responsibilities

  • Own agents end to end: scope business problems with operators and the product owner, set technical design, plan milestones, and lead development through launch and ongoing operation.
  • Make architecture decisions for each agent, including autonomy, agent loops, orchestration, stopping conditions, escalation paths, and steps that should be handled by deterministic code.
  • Design agents and tools for extension to new platforms and use cases; lead design and code reviews covering tool design, context engineering, state management, and failure handling.
  • Select and tune models according to quality, latency, and cost targets.
  • Own the design and roadmap for shared foundation components, including gateway action checks, identity and client-level access, durable pause-and-resume state, audit logging, and kill switches.
  • Shape how approved tools are exposed through MCP servers with scoped credentials, and lead technical work on the agent registry and observability layer.
  • Advise on build-versus-buy decisions for foundation capabilities based on cost, risk, and fit with the technology stack.
  • Define the security model for agents acting in client accounts, including least-privilege access, defenses against prompt injection and unsafe tool use, and approval rules for high-impact actions.
  • Define the team's evaluation framework for agent behavior, including task success, tool selection, trajectory quality, safety, and sandbox regression testing before release.
  • Set standards for tracing, metrics, and cost tracking so agent actions, rationale, duration, and cost can be inspected.
  • Own production health for agents led by the role, including incident response, post-incident reviews, and converting failures into evaluation cases, guardrails, or design changes.
  • Mentor engineers through pairing, design feedback, and code review; create reference implementations, templates, and documentation to help the team build agents more quickly and safely.
  • Partner with the Lead AI Engineer on technical roadmaps, sequencing, and estimates, and lead technical discussions with partner teams when needed.
  • Work with operators to understand their processes and design agents and human checkpoints around how work is actually performed.
  • Represent the team in architecture and security reviews with Information Security and Platform Engineering, contributing to shared standards for MCP policies, logging, environments, Databricks, and Lakebase.
  • Explain tradeoffs, risks, and progress clearly to operators, product partners, and leaders.

Benefits

  • Annual bonus opportunity of up to 25% of base salary.
  • Generous paid vacation policy.
  • 401(k) match program.
  • Health insurance options, inclusive of same-sex partners.
  • Family formation benefits, including reimbursement options for fertility, pregnancy, and parenting needs.
  • Monthly stipend for a mobile phone and data plan.
  • Sabbatical program.
  • Charitable giving through time and a financial match program.
  • Frequent paid travel to the Minneapolis headquarters for company, team, and in-person collaboration events.
  • Access to office spaces in Minneapolis, New York City, and Chicago.
  • Flexible work arrangement: office work on set days each week and an option to work remotely on other days.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service