Member Of Technical Staff – Agent Orchestration

Ovii's Interpretation of the Role

We need a systems‑focused engineer to own the stateful agent runtime that powers our conversational AI. You will design streaming pipelines, manage context persistence, and ensure low‑latency, reliable interactions.

Role Snapshot

• Stateful runtime ownership
• Real‑time streaming architecture
• Distributed systems coordination
• Latency & reliability focus
• Tool execution layer design
• Concurrency & state‑machine expertise

Must-Have Requirements

• Systems programming
• Real‑time streaming
• Stateful long‑running processes
• Distributed systems
• Debugging complex systems
• Concurrency (Elixir, Go, async)
• Message‑queue / event‑driven architecture
• real‑time streaming systems
• stateful long‑running processes
• distributed systems coordination

Nice-to-Have Signals

• Elixir/OTP
• LLM APIs and streaming protocols
• Conversational AI system experience
• NATS or Kafka
• Familiarity with our whitepaper on Stateful Agent Orchestration
• Elixir/OTP development
• LLM API integration
• conversational AI platforms

Work Setup

• Location: New Delhi, India
• Work mode: ONSITE
• Employment type: Full-Time

What You'll Likely Work On

• Own and evolve the stateful agent runtime, including streaming pipeline, state management, and tool execution
• Keep user view, model memory, and persisted state perfectly synchronized, even during mid‑response interruptions
• Build and refine the streaming architecture for buffering, delivery, and clean recovery on interruption
• Implement delivery pacing to make agent output feel natural rather than robotic
• Design the tool execution layer that calls domain‑specific tools mid‑conversation and reasons over results in real time
• Develop autonomous continuation logic so the agent decides when to keep talking or stop based on context
• Optimize latency and reliability metrics such as first‑token time, interruption recovery, and context‑window handling

Good Fit If You Have

• Enjoys deep debugging of low‑level concurrency issues
• Thrives in a fast‑paced, production‑critical environment
• Passionate about building conversational AI platforms