Founding AI Engineer (Agent Systems)

Vincer•Boston, MA

2d•$160,000 - $190,000•Hybrid

About The Position

Vincer is building a voice-first AI decision support system for life sciences sales reps who operate in complex environments. These reps need to navigate clinical evidence, competition, patient access, and regulated information, often making decisions alone in the field. The AI system must understand unstructured situations, assemble context, retrieve approved knowledge, orchestrate multiple AI systems, know when to escalate, and respond conversationally. The company is looking for a founding AI engineer to own the intelligence layer of this voice-first AI system and shape its AI direction. The role involves being one of the first two full-time engineers, inheriting existing work, and setting the AI roadmap. The system is agentic by design, meaning agents act based on rep activity and accumulated context, coordinate across models and data sources, and make judgments on handling, routing, or escalating issues. The challenge lies in making the system measurable, predictable, and safe in a regulated environment where errors have significant consequences.

Requirements

5+ years of full-time software engineering experience.
At least 2 years of recent, hands-on experience building and shipping AI systems in production (not prototypes or demos).
Experience designing or working with agentic systems: routing, tool use, retrieval, context management, and multi-step workflows.
Experience across multiple model providers and understanding of current agent tooling.
Located in Boston or NYC.
Understanding that regular, in-person collaboration is essential.
Willingness to own the intelligence layer and its associated accountability.
Ability to ship beyond the size of a small team using modern AI coding tools.

Nice To Haves

Experience in a startup environment at its earliest stages.
Enterprise software delivery experience, especially in a regulated industry (healthcare, finance, or similar).
Experience being responsible for an AI system after launch, not just through launch.
Comfort encoding expert judgment into measurable system behavior.
Experience with voice or other latency-sensitive interfaces.
Rigor about measurement and understanding of model-based evaluation strengths and limits.

Responsibilities

Own Vincer's intelligence layer: agent architecture and orchestration, evaluation, retrieval and grounding, guardrails, and AI quality.
Evolve the orchestration layer for independent versioning, deployment, and improvement of specialized agents.
Build evaluation systems to make agent quality visible, including failure modes, regressions, and impact of changes.
Build retrieval and grounding over approved customer content, treating unsupported answers as system failures.
Own guardrails, escalation logic, and safety behavior for a regulated environment.
Engineer for latency and cost through context management, caching, model selection, and routing across model tiers.
Encode expert judgment into system behavior, working with the scientific co-founder.