Platform AI Engineer / Full Stack AI Engineer

Experience: 2–3 years

Stage: Early-stage AI Startup

Team: Engineering / Product

Reports to: CTO / Founders

About the Role We are looking for an exceptional

AI Engineer who can build the technical backbone of our AI products from the ground up. This is not a traditional software engineering role. You will own the architecture, development, deployment, and scaling of AI-native products that combine

Voice AI Agentic workflows, backend systems, APIs, cloud infrastructure, and user-facing applications . You should be excited about building fast, shipping quickly, solving hard engineering problems, and working directly with founders to shape the company’s technical future.

What You Will Build You will help build:

• Enterprise AI Agents
• AI Voice Agents (real-time phone and voice automation)
• LLM-powered workflow automation systems
• AI copilots for enterprises
• Real-time conversational AI products
• Multi-agent orchestration systems
• Scalable AI infrastructure for enterprise deployment

Core Responsibilities 1. Build AI Products End-to-End Own the entire development lifecycle:

• Product architecture
• Backend APIs
• Frontend interfaces
• Database architecture
• AI model integrations
• Production deployment Take products from

prototype → MVP → enterprise-grade scale .

2. Build Production AI Systems Build systems using:

• OpenAI APIs
• Anthropic models
• Open source models via Hugging Face
• Agent orchestration frameworks
• Prompt chaining systems
• RAG architectures
• Context management pipelines Focus on reducing:
• Latency
• Hallucinations
• Token cost
• Model failure rates

3. Voice AI Infrastructure Build real-time voice systems using:

• Speech-to-text pipelines
• Text-to-speech pipelines
• Telephony APIs
• Voice conversation orchestration
• Real-time streaming architecture
• Interrupt handling in voice conversations Technologies may include:
• Twilio
• Deepgram
• ElevenLabs
• WebRTC infrastructure

4. Build Platform Infrastructure Design and build:

• Model serving infrastructure
• Agent orchestration engine
• Queue management systems
• Monitoring systems
• Failover systems
• Deployment pipelines
• Infrastructure automation Work with:
• Docker
• Kubernetes
• Redis
• Event-driven architecture
• Message queues
• Distributed systems

5. Move Fast We need engineers who:

• Build quickly
• Ship weekly
• Debug independently
• Solve product problems without waiting for requirements
• Take ownership beyond engineering This is a builder role.

Tech stack we use or want to build with: Backend

• Python
• FastAPI
• Node.js
• TypeScript
• PostgreSQL
• Redis

AI Stack

• LangChain
• LlamaIndex
• Vector databases
• RAG pipelines
• Prompt engineering
• AI evaluation frameworks

Frontend

• React
• Next.js
• TypeScript

Infrastructure

• Docker
• Kubernetes
• AWS
• CI/CD
• Terraform

Real-time Systems

• WebSockets
• WebRTC
• Streaming APIs
• Low latency systems

What We Want In Candidates Must have:

• Strong Python engineering skills
• Strong backend architecture experience
• Built scalable production systems
• Experience with LLM applications in production
• Ability to build across backend + frontend
• Comfortable in ambiguity Preferred:
• Worked in startup environments
• Experience in AI infrastructure
• Experience building agentic workflows
• Experience in voice AI systems
• Strong system design fundamentals