Posted on: 20/11/2026
Job Description:
Sense is hiring a Product Manager to own a major part of our Voice AI, LLM chatbot, and Agent Builder roadmap, from strategy and vendor decisions to delivery, quality, and customer outcomes.
About The Role:
You will work on Sense's conversational AI products and set direction for your area with Product Leadership.
- Voice AI and AI Receptionist: outbound and inbound agents that screen candidates, collect data, answer questions, and hand off to recruiters.
- LLM chatbots: web and SMS agents built on the same platform.
- Agent Builder: a modular platform (Greeting, Data Collection, Screening, FAQ, Closing) with custom instructions, prompt architecture, ATS variables, testing tools, and publishing into Sense Workflows.
- Voice stack: telephony, speech-to-text, LLMs, and text-to-speech from multiple vendors, where latency, voice quality, and cost per call are product decisions.
- Integrations: ATS field mapping and note writeback, which decide whether a good conversation becomes a usable record.
The work is hard because outputs are non-deterministic, calls happen in real time, and staffing customers run high volumes under consent and compliance rules.
You will work in the EPD (Engineering, Product, Design) triad with AI/ML, Customer Success, Implementation, and GTM teams.
What You'll Do:
Strategy:
- Own the roadmap and outcomes for one or more areas: voice agent quality and evals, Agent Builder platform capabilities, voice cost and architecture, or ATS and workflow integrations.
- Find where conversational AI can improve recruiter productivity, candidate experience, and outcomes such as screening completion and submission-to-placement conversion.
- Track advances in LLMs, speech models, and voice orchestration, and judge which are worth adopting.
Execution:
- Turn ambiguous customer and business problems into PRDs, user stories, and acceptance criteria that work for non-deterministic systems.
- Lead prioritization, sprint planning, and release coordination with Engineering, AI/ML, and Design.
- Work with QA on test coverage and run User Acceptance Testing before release.
Platform and vendors:
- Define agent behaviors, modules, prompt architecture, and guardrails with AI/ML and Engineering.
- Make build-versus-buy and vendor decisions for speech, voice, and LLM components, with cost and quality trade-offs modeled.
- Improve unit economics, including prompt efficiency and cost per call.
- Define call outcomes and classifiers, such as consent revoked, human contact requested, and logical completion.
- Own ATS integration behavior, including field mapping and writeback.
Quality, evals, and compliance:
- Build the approach to agent quality: call sampling, pre-release simulation, A/B testing, and voice-quality metrics.
- Improve observability so teams can see why a conversation went the way it did.
- Work with Legal and CS on consent, opt-out, and disclosure requirements.
Customers and stakeholders:
- Run discovery sessions, demos, and roadmap conversations with customers, recruiters, and Implementation teams.
- Triage escalations, spot patterns across support tickets, and turn them into product fixes.
- Support pilots and account health reviews, and present to executives.
Metrics you'll own:
Conversation outcomes:
- Connect rate, call and chat completion rate, drop-off by module, human handoff rate
Business impact:
- Screening completion, submission-to-placement conversion, recruiter time saved
Quality:
- Evaluation scores, voice-quality measures, interruption and latency quality, issue volume by theme
Reliability:
- ATS writeback success rate, platform and vendor uptime, escalation volume
Economics:
- Cost per call, gross margin per bot, LLM and speech cost per conversation
Trust:
- Opt-out and complaint rates, compliance check pass rate
Adoption:
- Active bots and accounts, time to launch a new bot, customer satisfaction
Qualifications:
Must have:
- BE/B. Tech or MBA, with 4 - 7 years of product management experience.
- Excellent academics.
- Shipped at least one LLM-powered, voice, or conversational product used by real customers.
- Practical understanding of prompt design, grounding, guardrails, and failure modes of LLM agents.
- Experience defining quality and evaluation approaches for AI or other non-deterministic systems.
- Hands-on experience working with LLM tools such as Claude, Gemini, and ChatGPT, for example through a personal, academic, or work project using LLM APIs, prompts, chatbots, or voice agents.
- Strong analytical skills, including SQL and working with API and integration behavior.
- Good system design skills and knowledge of the software development life cycle.
- Excellent written and oral communication, including executive presentations.
- Ability to prioritize and balance multiple tasks, work well in a team, and apply feedback constructively.
Nice to have:
- Experience with real-time voice systems such as telephony, speech-to-text, or text-to-speech.
- Experience with enterprise, multi-tenant configuration platforms.
- Exposure to HR tech, staffing, or high-volume candidate engagement.
- Familiarity with consent and compliance requirements for outbound calling and messaging.
Why join:
- You will work on products that talk to candidates at scale, with real customers and measurable outcomes.
- The team is small enough that you will influence architecture, vendor, and roadmap decisions early.
- Sense offers active mentorship, learning and development support, and a path to larger product leadership roles
Did you find something suspicious?