Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
ML Engineer @ Anuvaya LabsPosted 6 days ago

Member Of Technical Staff - Agent Orchestration

Who we'd reach at ML Engineer @ Anuvaya LabsFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Team lead

Runs the team day to day

Founder

Decides on early hires

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a full-time onsite role in New Delhi for an engineer who works on the runtime of a stateful conversational AI agent, covering streaming, state and tool execution. The team that owns the core runtime coordinates model calls, tool use, context, response pacing and conversation storage. The role calls for strong systems programming and experience with real-time or streaming systems.

What you’ll do

  • Own and evolve the stateful agent runtime, including the streaming pipeline, state management and tool execution layer.
  • Keep what the user sees, what the model remembers and what is persisted in sync, even when users interrupt mid-response.
  • Design how responses are buffered, delivered and recovered cleanly after an interruption.
  • Tune delivery pacing so responses feel natural rather than robotic.
  • Design the tool layer that lets the agent call domain tools mid-conversation.
  • Work on autonomous continuation logic that decides when the agent keeps talking or stops.
  • Optimize first-token time, interruption recovery and context window management.

What they’re looking for

  • Systems instincts around state machines, concurrency, race conditions and failure modes.
  • Experience building real-time or streaming systems, such as WebSockets or server-sent events.
  • Experience running stateful, long-lived processes in production.
  • Comfort with distributed systems, including message queues, event-driven architecture and service coordination.
  • Strong debugging skills for distributed systems.
  • Ability to read and reason about concurrent code in Elixir, Go or async runtimes.

Nice to have

  • Experience with Elixir and OTP, including GenServers, supervisors and the actor model.
  • Familiarity with LLM APIs and streaming protocols.
  • Experience with conversational AI systems beyond simple chatbot wrappers.
  • Experience with NATS, Kafka or other messaging systems.
  • Familiarity with the company's public writing on stateful agent orchestration.

What’s on offer

  • Onsite work from the team's office in Vasant Kunj, New Delhi.

Skills

Questions about this role

Is this role onsite?

Yes. The team strongly encourages everyone to be in the office.

What does the team own?

The team owns the core stateful agent runtime, which coordinates LLM calls, tool execution, context and delivery pacing.

Is Elixir required?

Elixir is listed as a bonus, not a requirement. Concurrent code experience in Elixir, Go or async runtimes is what the posting asks for.