Krisna Pranav

I’m Krisna Pranav, a senior AI/ML engineer at Turing.

I’ve been coding since 6th grade.

Email meMy résumé
Krisna, drawn in a hand-painted anime style: smiling in a white hoodie with headphones round the neck, at Marina Bay in Singapore, with the Merlion and Marina Bay Sands behind.

That first program grew into trading platforms, mobile apps and a desktop agent in Rust. Then came backends at , and AI labs work at that went into training frontier models. Today, at , I work directly with teams at Anthropic, OpenAI, Google and Meta.

It started in 6th grade.

I started out as an ethical hacker, a white hat.

The first language I ever learned was Scratch, blocks snapped together on screen. From there it was one project at a time, years before any of it became a job.

  1. 6th gradeWhite-hat hacking, and my first language, Scratch.
  2. 2017My first professional contracts.
  3. NowAgent infrastructure at Turing.

Things I’ve built.

I build agents that pick up where they failed.

Agentic workflows on Anthropic models, with durable state, so a long-running agent resumes after a failure instead of starting over. Underneath sit a gRPC routing layer and hot paths in Rust and C++, bridged to Python.

I work directly with teams at

  • Anthropic
  • OpenAI
  • Google
  • Meta
AI/ML EngineerNow
  • Rust
  • C++
  • Python
  • gRPC
  • PyO3
Stealth AI notetaker

I was the first engineer, from the first commit.

A VC-backed, privacy-first AI meeting assistant. One bot joins every call, and LangGraph agents turn live transcripts into summaries, action items and decisions.

It joinsZoomTeamsMeetPhone

Founding Engineer (#1)Jan 2025Jul 2026
  • Python
  • FastAPI
  • PostgreSQL
  • LangGraph
  • AWS

15 to 20Mrequests a day, moved from C++ to Go

Nothing went down.

Goroutines with bounded channels for backpressure, and a cutover that shifted traffic over in stages, with p99 latency on par with the legacy system.

Senior Software EngineerAug 2019Jul 2020
  • Go
  • C++

My work at Uber’s AI labs helped train frontier models.

Alongside it, model-driven services that make real-time decisions on high-traffic surfaces, held to tight latency budgets, and the Go and Python backends that serve them.

AI/ML EngineerMar 2024Aug 2026
  • Go
  • Python

I kept first tokens fast, under real load.

Forward deployed inside the teams at Handshake, Otter and Snorkel: a streaming gateway over WebSockets and SSE, and an embedding cache that ended full re-indexes.

AI/ML EngineerMar 2026Sep 2026
  • Python
  • Rust
  • TypeScript
  • SSE

I fix things upstream.

Two of my fixes are merged into Tauri and Playwright, frameworks a lot of engineers build on.

tauri-apps/tauri112K stars#15224

I stopped Tauri’s webview from leaking Objective-C retains.

Scoped Retained::as_ptr() bindings replace Retained::into_raw(), so WebContent processes are freed on macOS and iOS. RSS held flat over a 3-minute stress loop.

crates/tauri-runtime-wry/src/lib.rs

microsoft/playwright99.1K stars#41986

I made Playwright refuse navigations that crash Chromium.

Opening chrome://extensions from a non-persistent CDP context segfaulted Chromium. A per-browser blocklist turns the crash into an actionable error, with 7,800+ tests passing.

packages/playwright-core/src/server/chromium/crPage.ts

In the last year I made 1,712 contributions on GitHub, across 508 public repositories. My username OSINT tool, vesper, has 335 stars. Everything else is on my GitHub.

Every role since 2017.

8+ years of production systems, 4+ of them in AI/ML.

Résumé (PDF)
  1. AI/ML EngineerAgentic AI systems, LLM orchestration, production AI infrastructureNow
    • Agentic workflows and LLM orchestration on Anthropic models: multi-step reasoning, tool calling, and durable state that lets long-running agents resume after a failure instead of starting over.
    • The gRPC/REST layer that routes requests to agents, runs tasks concurrently, and defines the data contracts between services, so new workflows plug in without changes to the core.
    • Latency-sensitive infrastructure in Rust (async/Tokio) and C++, bridged to Python through PyO3/FFI for model integration and inference serving.
    • Rubric-based evaluation of model outputs, plus inference tuning, observability, and deployment for frontier-model work delivered to Anthropic, OpenAI, Google, and Meta.
    • Rust
    • C++
    • Python
    • gRPC
    • Anthropic
    See it in my work
  2. Crossing HurdlesAI/ML EngineerForward deployed on production AI for Handshake, Otter, and SnorkelMar 2026Sep 2026
    • Worked inside client engineering teams and closed every scoped task on their real-time inference and orchestration paths, in Python, Rust, C++, and TypeScript.
    • A streaming inference gateway that fans out concurrent LLM calls and streams tokens back over WebSockets/SSE, keeping time-to-first-token low under concurrent load.
    • An in-memory embedding cache and incremental re-indexing, so retrieval stayed fast as traffic grew and content updates no longer triggered a full re-index.
    • Python
    • Rust
    • C++
    • TypeScript
    • SSE
    See it in my work
  3. Stealth AI notetakerFounding Engineer (#1)VC-backed, privacy-first AI meeting assistant, built from zero to oneJan 2025Jul 2026
    • Made the architecture calls and shipped the product from the meeting bot to the user-facing app: Python/FastAPI services on PostgreSQL, Dockerized and deployed on AWS.
    • A bot that joins Zoom, Microsoft Teams, Google Meet, and phone (PSTN) calls on a shared SDK layer. Supporting a new platform meant writing one adapter, not another bot.
    • Live transcription streams into LangGraph agents that produce structured summaries, action items, and decisions, with sensitive meeting data kept under the user's control.
    • RAG over each user's meeting history, with Langfuse tracing on every LLM call so latency, token cost, and bad outputs trace to a specific prompt and step.
    • CI/CD, the automated test suite, and code-review conventions; mentored the engineers who joined next and worked directly with early users.
    • Python
    • FastAPI
    • PostgreSQL
    • LangGraph
    • AWS
    See it in my work
  4. AI/ML EngineerAI labs: work used to train frontier AI modelsMar 2024Aug 2026
    • Worked in Uber's AI labs, on work used to train frontier AI models.
    • Built and integrated model-driven services that make real-time decisions on high-traffic surfaces, working to tight latency budgets and reliability targets.
    • Data and inference pipelines behind ML features, and the Go/Python backends that serve predictions, alongside data science, infrastructure, and product teams.
    • Go
    • Python
    See it in my work
  5. Legal RAG platformAI/ML Engineer (Contract)Retrieval-augmented legal and compliance information systemJun 2021Jan 2022
    • A production RAG system answering procedural, compliance, and legal questions from a curated knowledge base. Every answer cites its source passage, so reviewers can check it.
    • The ingestion pipeline: PDF parsing, semantic chunking, metadata tagging (source, jurisdiction, document type), and embedding upsert into a hybrid vector + keyword store with reranking. Scanned pages go through vision-LLM extraction.
    • A scheduled monitoring agent that watches designated sources, detects new rulings, and re-indexes the live knowledge base, which ended manual upkeep of the corpus.
    • Python
    • RAG
    • Hybrid search
    • Vision-LLM
  6. Aether, AI desktop agentSenior Rust Engineer (Contract)On-device retrieval and vector searchSep 2020May 2021
    • A privacy-first desktop assistant in Rust: a local semantic engine indexes files, embeds them on-device, and answers context-aware queries with low latency.
    • The on-device HNSW vector index, for strong recall on large corpora without a GPU; owned packaging and release of the macOS/Linux binaries.
    • Rust
    • HNSW
    • Tauri
  7. Senior Software Engineer (External Contract)High-throughput backend migration from C++ to GoAug 2019Jul 2020
    • Migrated critical C++ services to Go on a tier handling 15 to 20 million requests/day, matching the legacy system's p99 latency while simplifying deploys.
    • Transaction-processing concurrency on goroutines with bounded channels for backpressure; ran the cutover with zero downtime by shifting traffic over gradually.
    • Go
    • C++
    See it in my work
  8. Earlier rolesContractsTrading infrastructure, full-stack web, mobile and blockchain20172019
    • A low-latency on-chain trading platform (Rust, Next.js/TypeScript).
    • Full-stack web (Next.js, React, Node.js, Python).
    • Production mobile and blockchain apps (Flutter, React Native, Solidity).
    • Rust
    • TypeScript
    • Flutter
    • Solidity

6th gradeWhere it started: my first program.

I specialise in production AI systems.

Eight years shipping production systems, four of them in AI/ML. I build the infrastructure under agents, the orchestration, the evals and the tracing, not a thin script on top.

A three-line LLM demo looks great for thirty seconds. The engineering starts when it meets real traffic: rate limits, slow tools, outputs that change between runs, thousands of concurrent users. I build for that part, and I write code other engineers can build on.

I do this for teams at Anthropic, OpenAI, Google and Meta.

  • Agentic AI and LLM orchestration, on frontier models, with durable state.
  • Distributed systems that stay fast under concurrency, and migrations that don’t go down.
  • Evals and tracing on every call, so a bad output points to one prompt and step.

Tools I reach for

I write

  • Python
  • Go
  • TypeScript
  • Rust
  • C / C++
  • SQL
AI and agents
  • LangGraph
  • LangChain
  • Claude / Anthropic
  • OpenAI
  • RAG with hybrid reranking
  • FAISS / HNSW
Distributed systems
  • Concurrency and backpressure
  • asyncio / Tokio
  • WebSockets / SSE
  • Zero-downtime migrations
  • Latency profiling
Cloud and MLOps
  • AWS
  • Azure (AKS / ACI)
  • Docker
  • Kubernetes
  • GitHub Actions
  • Langfuse evals
Backend and data
  • FastAPI
  • gRPC
  • REST
  • PostgreSQL
  • Redis
  • Neo4j

Off the clock, I trade, race and play.

I trade crypto, meme coins and the stock market.

  • Crypto
  • Meme coins
  • The stock market

I’m a professional sim racer.

6,250hours in CS:GO

1,250 hours in Fortnite

Where I’ve been.

I’m based in Singapore, where I work, and I travel often to Bengaluru. I’ve been to San Francisco too.

Marina Bay in Singapore as pixel art: Marina Bay Sands and its SkyPark, the ArtScience Museum, the skyline and the Supertrees, framed by palms and bougainvillea, under a golden-hour sky.
Singapore

Say hello.

I’m in Singapore. Email is the fastest way to reach me.

krisna.pranav@gmail.com
Email me