---
title: 'Member Of Technical Staff – Agent Orchestration at Anuvaya Labs'
canonical: 'https://feeny.ai/job/member-of-technical-staff-agent-orchestration-anuvaya-labs-delhi-zv8y3dr8bah4'
type: 'job'
last_seen: '2026-09-12'
---

# Member Of Technical Staff – Agent Orchestration at Anuvaya Labs

- **Company:** Anuvaya Labs
- **Location:** Delhi, India
- **Employment:** full-time
- **Work type:** onsite
- **Posted:** 2026-07-14
- **Last confirmed live:** 2026-09-12
- **Apply:** https://jobs.ashbyhq.com/anuvaya/a2ba988e-037a-4b1d-9e20-810cb02b454a

## Job description

## About Anuvaya

We think conversational AI agents will deliver all professional services in India. We started with astrology. We're a small group of engineers, designers, and product folks building at the intersection of conversational AI and domain expertise. Making an AI agent sound human-like is hard. Making an AI an expert in a domain is also hard. We're doing both together.

We're backed by Accel, Arkam Ventures, and Weekend Fund.

## The Role

Most AI agents treat conversations as stateless request-response cycles. Ours doesn't. We've built a stateful agent that streams responses with natural pacing, handles mid-response interruptions without corrupting state, decides autonomously whether to keep talking or wait, and maintains a living context that evolves across turns.

The Agent Orchestration team owns the core runtime - the system that coordinates LLM calls, tool execution, context management, delivery pacing, and conversation persistence. When you break something here, users notice in real-time. When you get it right, the agent feels like talking to a person who genuinely knows what they're doing.

## What You'll Do

- Own and evolve the stateful agent runtime - the streaming pipeline, state management, and tool execution layer
- Ensure what the user sees, what the model remembers, and what we persist stay perfectly in sync - even when users interrupt mid-response
- Build and refine the streaming architecture - how responses are buffered, delivered, and recovered cleanly on interruption
- Implement and tune delivery pacing - making the agent's output feel natural, not robotic
- Design the tool execution layer - the agent calls domain-specific tools mid-conversation and reasons over results in real-time
- Work on autonomous continuation - the agent deciding when to keep going and when to stop, based on conversational context
- Optimize for latency and reliability - first-token time, interruption recovery, context window management

## What We're Looking For

- Deep systems programming instincts - you think about state machines, concurrency, race conditions, and failure modes naturally
- Experience building real-time or streaming systems - WebSockets, SSE, or similar
- You've built and maintained stateful, long-running processes in production
- Comfort with distributed systems - message queues, event-driven architectures, service coordination
- Strong debugging skills for systems where "it worked on my machine" is never the problem
- You can read and reason about concurrent code - whether it's Elixir processes, Go goroutines, or async runtimes

Bonus

- Experience with Elixir/OTP - GenServers, supervisors, the actor model
- Familiarity with LLM APIs and streaming protocols (SSE, chunked responses)
- You've built or worked on conversational AI systems (not just chatbot wrappers)
- Experience with NATS, Kafka, or other messaging systems
- You've read our whitepaper on Stateful Agent Orchestration and can poke holes in it

## How We Work

We care about craft obsessively. Your work gets questioned, pulled apart, and rebuilt - not because we're harsh, but because everyone here holds each other to a standard most places don't bother with. We work out of a hacker house in Vasant Kunj. We strongly encourage everyone to be in office.

If that sounds like the only way you'd want to work - let's talk.

## About Anuvaya Labs

## Company Overview
- **One-liner**: Anuvaya Labs builds conversational AI agents that deliver professional services, starting with astrology and aiming to expand into other expert domains.
- **Entity Type**: Private (Unfunded / Bootstrapped) – has not raised any external funding rounds.
- **Headquarters**: New Delhi, India (office in Vasant Kunj).
- **Founded**: 2025
- **Founders**: Maahin Puri (CEO) and Nitesh Kumar Niranjan (CTO)

## Core Business
- **Primary Industry**: Conversational AI / Professional Services Automation
- **Target Customers**: B2C (end users seeking astrology/guidance) with eventual B2B expansion into other professional services (e.g., general medicine).
- **Mission Statement**: “We think Conversational AI agents will deliver all professional services in India.” – The company aims to make AI agents sound human-like while possessing deep domain expertise.

## Products & Services
- **Vaya** – A conversational AI agent for astrology. Users interact via natural language to receive personalised astrological insights.
- **Terra** – An open-source multi-agent SDK (built on Elixir `gen_statem`) for orchestrating stateful, interruptible, and context-aware conversations in production.
- **Rune** – An append-only knowledge graph providing long-term memory for AI agents. Captures how a user’s life evolves over time, deterministic and causal.
- **RCE (Realtime Context Engine)** – A system that feeds live, streaming context into agents so they reason on current information, not stale data.

## Market Standing
- **Valuation / Market Cap**: Not publicly available (unfunded).
- **Key Metric**: No disclosed revenue; total funding is $0 (self-funded / bootstrapped).
- **Notable Investors / Partners**: No institutional investors. The company states it “works with best investors” but no names are public; Tracxn confirms no funding rounds.
- **Growth Signals**:
  - Small team (3 employees per LinkedIn) with 25% monthly employee growth (indicating early-stage expansion).
  - Published open-source projects (Terra, Rune) attracting developer attention.
  - Strong engineering blog (inside.anuvaya.com) with deep technical content on multi-agent orchestration.

## Competitive Advantages
- **Deep Domain + AI**: Combining conversational AI with expert domain knowledge (starting with astrology) creates a moat in verticalised professional services.
- **Proprietary Infrastructure**: Owns Rune (long-term memory), RCE (real-time context), and Terra (multi-agent framework) – not just a thin wrapper on LLMs.
- **First-Principles Approach**: The team prides itself on deconstructing problems to fundamental truths, leading to unique architectural decisions.
- **Talent Density**: Deliberately small, flat team of A-players; no rush to hire.

## Strategic Focus
- **Immediate**: Scale the astrology product (Vaya) to a mature, widely used service in India.
- **Medium-Term**: Expand into other professional services (e.g., general medicine) using the same conversational AI platform.
- **Long-Term**: Become the infrastructure layer for AI-delivered professional services in India.

## Why Work Here
- **Culture**: High-obsession, craft-first environment. Work gets “questioned, broken down, rebuilt.” Not a 9-to-5 role; expect to think about problems after hours.
- **Work Model**: On-site only (hacker house in Vasant Kunj, New Delhi). No remote or hybrid options.
- **Team**: Extremely small and flat. Engineers, designers, and product folks work closely together.
- **Engineering Culture**: Heavy focus on building in public (open-source contributions, detailed blog posts). Use of technologies like Elixir, knowledge graphs, and real-time streaming.
- **Ideal For**: Someone who craves deep technical challenges, doesn’t mind ambiguity, and wants to shape the foundational architecture of a young company.

## Sources
1. [anuvaya.com](https://anuvaya.com/) – Company website, culture page, product descriptions
2. [linkedin.com/company/anuvaya](https://www.linkedin.com/company/anuvaya) – LinkedIn company profile, employee count, growth data
3. [builtin.com/company/anuvaya-labs](https://builtin.com/company/anuvaya-labs/) – Company overview, office location, career page
4. [inside.anuvaya.com](https://inside.anuvaya.com/) – Engineering blog detailing Terra, Rune, RCE, and multi-agent architecture
5. [tracxn.com/d/companies/anuvayalabs](https://tracxn.com/d/companies/anuvayalabs/__pBjcVxbTxax2dVOOGhUX9kFNcXohrWvGvWQNeqjf3gw) – Tracxn profile confirming unfunded status, founding details, and legal entity

## Other roles at Anuvaya Labs

- [Strategy & Operations Lead](https://feeny.ai/job/strategy-operations-lead-anuvaya-labs-delhi-43jjyh7ak2yy) — Delhi, India
- [Member of Research Staff](https://feeny.ai/job/member-of-research-staff-anuvaya-labs-delhi-9r5rvt9d1ea3) — Delhi, India
- [Member of Product Staff - Product Lead at Anuvaya](https://feeny.ai/job/member-of-product-staff-product-lead-at-anuvaya-anuvaya-labs-delhi-pgr3p3979cse) — Delhi, India
- [Member of Technical Staff - Applied AI Research](https://feeny.ai/job/member-of-technical-staff-applied-ai-research-anuvaya-labs-delhi-n6k9ggwjnpje) — Delhi, India
- [Member of Technical Staff - Product Engineering](https://feeny.ai/job/member-of-technical-staff-product-engineering-anuvaya-labs-delhi-7s36c32z6njs) — Delhi, India
- [Member of Growth Staff - SEO](https://feeny.ai/job/member-of-growth-staff-seo-anuvaya-labs-delhi-heydbeg12g98) — Delhi, India