About The RoleTake2 AI is hiring a Senior Software Engineer, Applied AI with deep experience applying agentic AI solutions with multi-agent / RAG in production to design, build, and scale the AI systmes powering Take2's autonomous healthcare recruiting platform.
You'll own applied-AI work end-to-end - from prototyping and model selection through production reliability - as we scale from thousands to millions of candidate conversations.
This role is high-ownership, hands-on, highly technical, and perfect for someone who thrives in a startup environment, playing a key role from design through production with significant ownership over technical execution and direction.
In Terms of ExperienceRequired:- 6+ years software engineering experience (backend or full stack) with significant ML and Applied AI experience as a part of that
- Bachelor's in Computer Science or Computer Engineering
- Have shipped multi-agent AI solutions with real-time inference to live users at scale
- Designed and implemented agent orchestration, evaluation frameworks, and related tooling
- Shipped production AI applications with real-time inference, integrating ML models into live systems
- Built and operated distributed backend systems with monitoring and observability in place
- Strong proficiency in Python, JavaScript, Node.js, AWS, Kubernetes, Docker
- 2+ years at an early to mid-stage startup (Series B or lower)
Preferred:- Experience self-hosting AI/ML models for use in voice AI pipelines, including tuning and optimizing them for performance and reliability
- Experience owning and operating distributed systems in high-throughput, streaming, low-latency environments, ensuring scalability, reliability, and performance under real-time constraints
- Direct, hands-on experience integrating and optimizing STT, TTS, VAD, and LLMs for real-time voice agents
- Scaled and optimized voice pipelines for low latency, high availability, and real-time performance
What You'll Do- Design and build applied AI-powered features and agentic workflows - tweak systems, use RAG, build intra-agent networks & communication - and ship them to production
- Select, integrate, evaluate, and tune models for the right balance of quality, latency, cost, and reliability across voice AI pipelines (STT/TTS/VAD)
- Build evaluation, guardrail, and observability systems to ensure AI behavior is measurable and safe at scale
- Own the backend services and data/inference pipelines that serve applied-AI features in production
- Collaborate closely with product and founding engineering to rapidly prototype and deliver with significant ownership over technical direction
Location & FlexibilityWe're NYC-based and work hybrid (in-office Mon-Thu). We value in-person collaboration but also trust people to manage their time responsibly.
Compensation & GrowthCompetitive salary + meaningful equity. This is a chance to join at a stage where your work meaningfully shapes the product and your career trajectory.
