Swoyam
Siddharth Nayak
I build the backend that powers Sarvam's Samvaad conversational-agent platform — low-latency voice-to-voice pipelines, agent tooling, and the LLM layer behind India's sovereign AI.
Computer Science graduate from IIIT Bhubaneswar (Class of 2025), now a software engineer at Sarvam AI — contributing to India's sovereign LLM under the IndiaAI Mission.
My focus is turning cutting-edge generative-AI research into real-world systems with tangible user impact: real-time voice agents, an agentic authoring copilot, a multi-provider LLM abstraction, and the analytics that keep it all measurable. I started full-stack — Flutter apps, FastAPI backends, event automation — and carried that build-anything instinct into AI infrastructure.
Off the critical path, I've led as Tech Secretary and Placement Coordinator at IIIT Bhubaneswar, shipped campus-scale apps used by thousands, and written about the things I build.
What I've built on the Samvaad platform
The conversational-agent stack that turns text prompts into production voice agents — the pieces I've owned end to end.
Native function-calling agent
Re-architected the core conversational agent from a two-agent (action + tool) design into a single native tool-calling agent with pluggable streaming/unstreaming adapters, across the voice-to-voice and WhatsApp/text pipelines — removing a per-turn hop and cutting latency.
Samvaad “Copilot” (Improve-with-AI)
A pydantic_ai orchestrator that streams edits over WebSocket and mutates live agent state-machine config through typed tools (edit-state, update-variable, edit-global-instruction) over Gemini 2.5 / Claude Sonnet 4 — cutting agent authoring from ~7 days to 1–2 hours.
Playground v2
Conversation forking & branching — replay any interaction to a chosen turn and fork new state, with Redis state-machine hydration — plus history review, bookmarking, and ClickHouse/Redis-backed debug-interaction management.
sarvam-llm abstraction
A multi-provider LLM abstraction over LiteLLM (AWS Bedrock, Google Vertex, Anthropic Claude, Azure/OpenAI) with automatic fallback chains, native function-calling, structured output, tuned httpx pooling, and Prometheus metrics for token usage, inter-token latency, and time-to-first-speech.
Barge-in & background noise
Real-time interruption handling that truncates the assistant turn at the exact played-character boundary and reconciles the LLM thread for seamless resumption — plus a background-noise system that dynamically mixes ambient audio into the TTS stream for acoustic realism.
Interaction ClickHouse data model
Designed the interaction-turns and interaction-event ClickHouse model — per-turn and per-event tables capturing per-modality model, pipeline, and TTFB/TTFV latency across the ASR, LLM, tool, TTS and translate stages — surfaced through Metabase dashboards that drive product decisions.
Post-call structured extraction
Dynamically builds a Pydantic schema from each agent's variable config and drives typed LLM extraction from call transcripts — turning free-form conversations into structured, queryable outcomes.
Extension Service
A Streamlit multi-app platform with dynamic app routing, Flagsmith-driven org entitlement, and shared JWT auth inside the NextJS platform — letting client-specific tools ship without forking the core app.
Where I've worked
Software Engineer · Sarvam AI
Jun 2025 — PresentAI Intern · Sarvam AI
Dec 2024 — May 2025AI Intern · MLOps & GenAI · FixIt-AI
Aug 2024 — Nov 2024Project Intern · Oracle NetSuite
May 2024 — Jul 2024Jr. Flutter Developer · EzTruck
Jul 2023 — Oct 2023Core Team Lead · Codeate.in
Jun 2021 — Jul 2022Things I've shipped
Side projects, campus-scale apps, and experiments — many still live.
Sifra
A personal AI assistant.
Sentry Auto-Triage Bot
FastAPI webhook that ingests Sentry issues, resolves the offending source frame, pulls code from GitHub, and posts an SRE-style Gemini root-cause card to Slack.
AI Storyboarding
Turns story ideas into full storyboards with Gemini for scenes and DALL·E 2 for visuals.
Job News
A backend service surfacing curated job news.
IIIT-Bh Learn
A learning platform for IIIT Bhubaneswar.
IIIT Everything
A campus super-app on the Google Play Store.
DevFest '23 App & Web
Website and check-in app for GDG Bhubaneswar's DevFest.
Advaita Fest
Website plus a passes & check-in system for IIIT-BH's annual fest.
File Manager
A self-hosted file-management service.
Disease Prediction
An ML API predicting diseases from symptom inputs.
Epidemic Prediction
A model for forecasting epidemic spread.
SmartConnectify
A connectivity-focused mobile application.
From the blog
Notes on the things I build — mostly Python, automation, and infrastructure.
Skills & stack
B.Tech, Computer Science Engineering
International Institute of Information Technology, Bhubaneswar
Senior Secondary (PCM + CS)
Kendriya Vidyalaya No. 3, Bhubaneswar
Secondary
Kendriya Vidyalaya No. 2, AFS Maharajpura, Gwalior
Communities
Precision Agriculture: ML & DL-based Detection and Classification of Agricultural Pests
Novel hybrid ML/DL model (EfficientNetB0 + XGBoost) classifying 12 agricultural pest categories.
96.7% early-detection accuracy, beating individual CNN and ML baselines.
Google Hash Code 2022 — Qualification Round
Built an optimized solution to a large-scale logistics problem under time constraints in the global team programming competition.
What people say
“An exceptional individual — consistently outstanding organisational skills in managing our GDSC team, with seamless execution, hard work, and real leadership.”
“One of the hardest-working talents I've worked with — always on edge to go the extra mile and learn to get things done.”
“'Highly efficient' is the phrase that comes to mind. As Core Team Lead he showed deep command of core concepts and shipped real technical solutions — apps, websites and more.”
Let's build something.
Open to interesting problems in voice AI, backend optimization, and real-time systems.