Skip to content
View mangeshraut712's full-sized avatar
💼
Open to Software Engineer roles
💼
Open to Software Engineer roles

Block or report mangeshraut712

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mangeshraut712/README.md

Mangesh Raut — Software Engineer

Important

Open to Software Engineer roles (Pune · Philadelphia · remote). Portfolio systems: real-time speech VAD with an F1 gate, offline RAG eval, agents with tool calling and failure handling, and the full stack around them. Benchmark figures link to their reports or CI runs; account statistics link to dated snapshots. Stub metrics are labelled stub.

Fastest contact: mbr63drexel@gmail.com

Portfolio LinkedIn Instagram WhatsApp X Email

GitHub Sponsors Stripe PayPal Buy Me a Coffee


Start here — three systems, end to end

Project What it proves Guardrails Proof
ai-ml-portfolio — speech VAD + RAG eval + NumPy ML from scratch Measured VAD F1 gates (real audio + synthetic labels). Offline RAG/LLM eval with retrieval metrics; CI uses stub providers Acceptance gate fails CI below fixed thresholds; eval falls back to stubs when keys are missing MODEL_CARD · RESULTS
agent-console · Incident Desk — seeded on-call investigation + protocol console Labelled, key-free replay of Northwind incidents; planner/tool trace, verdict and seed-based scorecard Live-capable Nemotron planner via Nebius (not executed); telemetry stays seeded. Original WebSocket reorder/dedupe and RESUME console retained Agent implementation · Protocol decisions · Pages replay demo
Gravity-SaaS-Agent — multi-tenant agent SaaS starter MCP-style simulated tool registry, skills scaffold, billing events, operator dashboard Tier rate limits, Supabase RLS policies, OpenRouter retries/circuit breaker and labelled echo fallback. Channel adapters are simulators, not live Business API README · CI

Run the benchmark and acceptance gates (Python 3.10–3.12, no API keys; latency depends on hardware):

git clone https://github.com/mangeshraut712/ai-ml-portfolio && cd ai-ml-portfolio
make install && make verify-all      # mlfs tests + VAD FULL_PASS + offline LLM eval

On Debian/Ubuntu, install build-essential and libsndfile1 first. Initial setup needs network access for dependencies and audio.


Engineering metrics — measured, with baselines and a failure case

Source audit and verification limits · checked November 3, 2026.

Verified engineering metrics

The VAD figures come from Sep 11, 2026 CI. Latency measures batch whole-file processing and excludes warmup; the VAD gate runs on Python 3.11. Exact labels are constructed from real speech and synthetic silence; soft labels use energy, not human annotation. Baselines and failure cases:

Metric Measured Gate / baseline Source
VAD exact F1, noisy — known failure mode 0.7768 ≥ 0.75 (clean ≥ 0.92) challenge_pass.py · MODEL_CARD
VAD soft F1 0.8135 ≥ 0.78 same
RAG retrieval (offline stub) — TF-IDF Recall@5 · MRR · nDCG@5 1.000 · 0.981 · 0.986 40 gold QA + 15 adversarial on 10 FAQ docs. BM25-fusion stub Recall@3 0.975. Hallucination 0.000 = stub abstaining RESULTS.md (STUB, 2026-07-24) · DATA_CARD
Stub cost / latency matrix Stub p95 ms and estimated $/1k queries from configured prices/token estimates live path is EVAL_LIVE=1; CI forces EVAL_LIVE=0 (stub) same RESULTS.md
CI labs + VAD acceptance gate green — Sep 11, 2026

Open-source contributions

42 / 50  ████████████████▊░░░  84%

By organization (allowlist scoreboard)

Org GitHub merged Focus
AWS Labs 11 MCP, Stickler, billing-cost fixes & Visual Asset Management System
Microsoft 8 hve-core, winget-pkgs, physical-ai-toolchain, Semantic Kernel
Apple 7 Password-manager resources & schema
NVIDIA 4 CUDA Python tests & TensorRT tooling/CI
Adobe 3 React Aria / Spectrum (incl. ColorField Form validation)
Google 2 sbsim BUILD cleanup + Gemini cookbook link checker
Sarvam AI 2 Cookbook CI
OpenAI 1 codex-security CLI guidance
Moonshot 1 kimi-code models.dev fallback
Samsung 1 CredSweeper install-guide docs
Meta 1 Lexical; plus 14 accepted Pyrefly CodeSync landings on main (separate)
Netflix 1 DGS codegen Kotlin client generation

Open pull requests: 88 across allowlist orgs, including Anthropic (11), Walmart (4), xAI (2), JPMorgan (2), Tesla (1) and LG/webOS (1).

Selected Engineering Impact

Five merged upstream fixes, with regression tests, corrected assertions or schema validation.

Meta · Lexical — meta/lexical#9707
  • Problem: When the caret sat after a block decorator inside an element whose DOM slot has a before boundary, the block cursor got appended after the slot's trailing decoration, outside the range the editor manages (#9680).
  • What I did: Changed $updateDOMBlockCursorElement to insert the cursor before slot.before, falling back to append when there is no boundary or it was detached. Added unit tests for both cases.
  • Result: Merged by @etrepum. The new test fails before the fix and passes after, and the lexical, rich-text and selection unit suites stay green. Custom slot layouts now keep the cursor where the editor expects it.
Netflix · DGS Codegen — Netflix/dgs-codegen#997
  • Problem: Kotlin 2 client generation always added _alias and _projection parameters to projection methods, so a GraphQL field with an argument of the same name produced duplicate parameters and failed to compile (#930).
  • What I did: Renamed the generated alias and projection parameters only when they collide with a field argument, so existing schemas keep the same names. Added codegen tests that compile client queries using _alias and _projection arguments.
  • Result: Merged by @iuliiasobolevska, who kept the commit and added a follow-up for related shadowing cases. Slated for the 8.8.1 release.
Microsoft · Semantic Kernel — microsoft/semantic-kernel#14668
  • Problem: The Python OpenAPI plugin checked allowed_base_urls with a raw path-prefix match, so /api/../admin and /api/%2e%2e/admin passed an /api allowlist. For the literal dot-segment path, httpx actually requested /admin (#14662).
  • What I did: Checked the prefix after dot-segment normalization in both raw and percent-decoded forms, preserving internal empty segments to match httpx. Added tests for the escapes and for paths that must still pass, like /api/./users and /api/.
  • Result: Merged by @eavanvalkenburg. The tested dot-segment escapes are rejected by the OpenAPI URL allowlist, and /apiusers is still rejected.
AWS · MCP servers — awslabs/mcp#4849
  • Problem: On Windows, the postgres-mcp-server PG-wire path broke because psycopg's async mode does not support the default Proactor event loop (#4825).
  • What I did: Set WindowsSelectorEventLoopPolicy at the start of the server entry point, before startup validation or MCP creates a loop, so other platforms keep their default. Added mocked tests for both the Windows and non-Windows paths.
  • Result: Merged by @kennthhz. The PG-wire startup path now selects the Windows event-loop policy required by psycopg; mocked tests cover Windows and non-Windows policy selection.
Adobe · React Spectrum — adobe/react-spectrum#10863
  • Problem: React Aria's ColorField ignored a parent Form's validationBehavior, unlike TextField and NumberField (#10862).
  • What I did: Read FormContext through useSlottedContext and resolved the value as prop, then form, then 'native', matching the other fields. Added a regression test that validationBehavior="aria" gives aria-required without native required.
  • Result: Merged by @devongovett. ColorField now inherits Form ARIA validation behavior, matching the existing TextField and NumberField pattern.

More projects

More projects: Hindai, Stanford CS336, Codex Insights, Vitals.AI, erdos142, sarvam-ai-cookbook

  • Actions Nurse — Open Agent Hackathon 2026 Wildcard track (author-recorded submission: 28 Oct 2026 4:30 AM IST, hub). CI triage agent: Rules + optional Gemma, Meterless H-MEM, labelled Zetaris fixtures with optional live read-only evidence. submission stamp.

  • Asset Intelligence Copilot — FlytBase challenge entry (AI Hackers Collective × Hacktoberfest 2026 Hack Day). Chat copilot for oil-field operators: deterministic tools compute numbers, answers cite record IDs and SOP passages, Gemma 4 for planning/phrasing. Local; MIT.


Architecture — patterns across these projects

Conceptual patterns across separate projects; arrows do not assert one integrated deployment.

flowchart LR
  subgraph Client
    B[Browser<br/>Next.js · React]
  end
  subgraph Runtime
    WS[WebSocket agent server<br/>seq ordering · RESUME replay]
    API[FastAPI / Express gateway<br/>rate limits · RLS · circuit breaker]
  end
  subgraph Models_Tools_Data["Models · Tools · Data"]
    OR[OpenRouter / Workers AI<br/>project-specific routing]
    MCP[MCP servers · tool calling]
    VAD[WebRTC VAD · speech]
    RAG[BM25 / TF-IDF retrieval<br/>eval gates]
  end
  subgraph Ops
    CI[GitHub Actions CI<br/>F1 gates · offline eval]
    DEP[Docker · Cloudflare · GitHub Pages]
  end
  B <--> WS
  B --> API
  WS --> MCP
  API --> OR
  API --> RAG
  B --> VAD
  MCP --> OR
  CI --> DEP
Loading
AI engineering stack — tools and dependency evidence

AI stack

The card lists tools I use or explore. The manifests below verify declared dependencies in these repos, rather than installed versions or live deployment.

Stack claim Source
NumPy · webrtcvad · rank-bm25 · scikit-learn ai-ml-portfolio/pyproject.toml
Next.js 16.4.3 · React 19.1 · Turbopack agent-console/package.json
Next.js 15.5 · React 19.2 · Cloudflare Workers AI Hindai/package.json · workers/hindai-gemma
Next.js 16.4 dashboard · Express gateway · Supabase Gravity-SaaS-Agent/apps
FastAPI mangeshrautarchive/requirements.txt · career-agent-pro/backend
Sarvam SDK Realtime_Speech_Captioning/requirements.txt
Now — what I'm building in Q4 2026

Currently building

Principles, writing, trajectory

Engineering principles

  • Measure everything; ship the gate with the number
  • Local-first whenever possible; CI must not depend on a live API
  • Reliability over novelty — an agent with guardrails beats a flashier one without
  • AI should augment, not obscure, the system
  • Developer experience matters; simple systems scale better

Details: INTERVIEW_NOTES.md

Writing

Trajectory

Contribution trajectory by year

Contribution graph · yearly snapshot JSON

Pinned Loading

  1. Gravity-SaaS-Agent Gravity-SaaS-Agent Public

    Multi-tenant SaaS AI agent platform: MCP, WhatsApp, billing — Next.js + TypeScript

    TypeScript 8 4

  2. mangeshrautarchive mangeshrautarchive Public

    Agentic full-stack portfolio & open-source engineering chronicle: Vanilla ESM, FastAPI, OpenRouter (grok-4.3), WebMCP tools, Apple HIG glassmorphism, and 100/100 Lighthouse CI

    JavaScript 1

  3. AssistMe-VirtualAssistant AssistMe-VirtualAssistant Public

    Multi-modal AI assistant with voice mode and research tools (React + FastAPI).

    JavaScript

  4. Hindai Hindai Public

    Hind AI digital gurukul — interactive learning for Indic scriptures with local Gemma via Ollama (Next.js).

    TypeScript

  5. Stanford-CS336 Stanford-CS336 Public

    Self-study notes and labs for Stanford CS336: language modeling, transformers, GRPO, BPE

    Python 3

  6. erdos142 erdos142 Public

    Erdős problem 142 research notebook — OPEN (single final obstruction). Audits, verifiers, roadmap. © Mangesh Raut

    Python