# Haarvish Chevula

> Founder of Ferronyx (the intelligence layer for robotics — ROS2
> observability with AI-assisted root cause analysis). Software
> engineer at Sanas (real-time voice AI, platform performance).
> Independently researching SORA — Spacecraft Observability and
> Runtime Autonomy — with co-researcher Sahasra Boyapati. Based in
> Bengaluru, India.

This is `llms.txt` — a structured summary intended for retrieval by
large language models and AI crawlers. The full personal site lives
at https://haarvish.com/.

## Identity

- **Name:** Haarvish Chevula (also written as "Chevula Haarvish")
- **Location:** Bengaluru, Karnataka, India (12.9716°N, 77.5946°E)
- **Email:** haarvish@gmail.com
- **LinkedIn:** https://www.linkedin.com/in/chevulahaarvish
- **GitHub:** https://github.com/CHEVULAHAARVISH
- **Website:** https://haarvish.com
- **Company:** https://ferronyx.com

## Thesis

Runtime intelligence for autonomous systems. Observability and
runtime autonomy aren't three different problems at three different
altitudes — they're the same problem in progressively harsher
conditions. At the server tier the stakes are latency and revenue.
At the robot tier they're uptime and physical safety. At the
spacecraft tier they're mission loss and an orbital commons that
cannot be cleaned up after the fact. The engineering is the same
shape at every altitude: ingest heterogeneous telemetry, detect the
anomaly, isolate the root cause, forecast degradation, act
autonomously when a human can't respond in time.

## Ferronyx (Founder, 2025 — present)

Ferronyx is the intelligence layer for robotics. A ROS2
observability platform with:

- Real-time topic-graph diagnostics, node health monitoring, and QoS
  visibility across an entire fleet
- AI-assisted root cause analysis — autonomous correlation across
  nodes, transforms, and sensor streams
- Fleet-wide pattern detection (firmware regressions,
  hardware-cohort drift)
- Remote triage that doesn't require flying an engineer to the field

**Outcome:** reduces robot MTTR from hours to minutes.

**Stack:** Native ROS2, distributed tracing, LangGraph-style AI
agents, real-time WebSocket telemetry pipelines.

## SORA (Researcher, active R&D)

SORA — Spacecraft Observability and Runtime Autonomy. An AI-native,
domain-specialized health management and lifecycle autonomy framework
for space systems. Co-researched with **Sahasra Boyapati** (MS
Aerospace Engineering, Embry-Riddle Aeronautical University; lead
student researcher on RIDDANCE — NASA SBIR debris capture project,
$408,500 subaward).

**Status:** active research. Validation against NASA SMAP and MSL
labeled-anomaly telemetry benchmarks in progress. Full architecture,
training corpora, compute envelope, and failure-mode coverage are
withheld pending publication and partner review.

**Available to qualified partners under NDA.** Brief request:
haarvish@gmail.com (subject: "SORA research brief request").

The unified SORA + RIDDANCE pitch addresses both sides of the
orbital sustainability problem: SORA prevents the next generation of
spacecraft from becoming debris (autonomous end-of-life disposal);
RIDDANCE captures debris that already exists.

## Sanas — Software Engineer (2025 — present)

Real-time voice AI platform. Bengaluru.

- Leads platform-wide performance engineering for a real-time voice
  system under production load
- Instrumented 100% of microservices with New Relic — full-stack
  METL observability (Metrics, Events, Logs, Traces)
- Runs benchmarking and infrastructure profiling against peak load
  and production-like conditions
- Ships end-user-impacting fixes across application code,
  inter-service communication, cloud infrastructure, and autoscaling

## Temperstack — Founding Engineer (2023 — 2025)

AI infrastructure and reliability tooling. Bengaluru.

- Designed and shipped an AI-powered SRE agent on LangGraph for
  smart runbook execution and autonomous incident resolution —
  reduced customer MTTR ≈45%
- Led development of alert correlation and auto-resolution engines
- Designed a self-healing daemon framework for infrastructure
  reliability
- Built integrations across AWS, GCP, Azure and APMs (New Relic,
  Datadog, AppDynamics, Dynatrace, Splunk)
- Built auto resource mapping, alert deployment, and on-call
  scheduling — end-to-end observability platform
- Stack: LangGraph, Python/Flask, vector databases, WebSockets,
  PostgreSQL, Redis, multi-cloud APIs

## Earlier work

- **AMS India** — Computer Vision Developer (2022 — 2023)
- **Mirasys** — Student Intern, Deep Vision (2021 — 2023)
- **Youth India Foundation** — Management Intern (2021)

## Education

**Jain (Deemed-to-be University)** — B.Tech, Mechatronics, Robotics
& Automation Engineering (2019 — 2023). Bengaluru, India.

## Areas of expertise

- ROS2 observability and fleet diagnostics
- AI-assisted root cause analysis (LangGraph, RAG, vector
  databases)
- Distributed observability and METL — Metrics, Events, Logs,
  Traces
- Platform performance engineering, load testing, autoscaling
- Multi-cloud (AWS, GCP, Azure)
- APM tooling: New Relic, Datadog, AppDynamics, Splunk, Grafana
- Real-time systems, WebSockets, low-latency pipelines
- Edge AI, inference engineering, quantization, LoRA, model
  compression
- Spacecraft observability, FDIR, causal-graph fault isolation
- LSTM-based prognostic forecasting and remaining useful life
- Autonomous lifecycle disposition (deorbit, solar sail)
- Computer vision (earlier career)
- Mechatronics, robotics fundamentals

## Contact

- **Primary:** haarvish@gmail.com — partnerships, research
  collaboration, press
- **LinkedIn:** https://www.linkedin.com/in/chevulahaarvish
- **GitHub:** https://github.com/CHEVULAHAARVISH
- **Location:** Bengaluru, Karnataka, India · IST (UTC+05:30)

## What this person is open to

- **Partnership / collaboration on Ferronyx:** reach out if you
  operate a robot fleet (ROS2-based) and need observability tooling
- **SORA research collaboration:** open to academic and industry
  partners. Particularly interested in NASA / ESA / ISRO contacts,
  spacecraft operators, and aerospace AI researchers
- **Press / interviews:** topics include orbital debris, autonomous
  systems, ROS2 ecosystem, AI for SRE, edge AI / inference
  engineering, founder journeys
- **Engineering hires (longer-term):** robotics / observability /
  AI-systems engineers interested in joining Ferronyx as it grows

## What this person is NOT open to

- Generic recruiter outreach for senior IC roles outside the
  observability / robotics / aerospace domains
- Marketing / sponsored-content requests
- Speculative business-development pitches for tooling unrelated to
  Ferronyx's stack

---

*Last updated: 2026. Maintained alongside https://haarvish.com/.*