Builder
Next.js frontends, NestJS and FastAPI services, a Python RAG pipeline, Helm charts. I wrote 97% of the old frontend and 70% of the new one.
Product engineer · BHyve
I build AI products that stay fast, accurate and cheap at scale.
Product engineer and team lead at BHyve, a knowledge platform for enterprise teams. In five years I've gone from intern to owning the AI answer engine, a large share of the platform it runs on, and most of our releases. I measure before I change anything, and I write down what I find.
AI search and RAGCost optimisationPlatform engineeringTeam leadRoadmap planning
Akash DahadProduct engineer, team lead
CompanyBHyve, since Sep 2021
FocusAI search, cost, platform
StackNext.js · Python · LLMs · K8s
DegreeBE Computer Science, GEC Aurangabad
AwardWinner, Smart India Hackathon 2020
Impact
The numbers I'm proudest of.
Each one links to the story behind it.
−75%idle AI compute pods: three deployments became one shared service−83%memory requested by the extraction service, across three environments5–6 msvector search, flat from 100,000 to 500,000 rows$0.0012measured cost of one knowledge-base answer+26%more correct answers in Smart mode on a real customer question set40×faster extraction for born-digital PDFs on the new Lite tier−71%CI minutes billed for a one-app deploy13 / 15pentest findings closed one day after the test ended
Case studies
The work, and the thinking behind it.
Jan – Sep 2026 · 9 months
Bringing server costs down, service by service
−75%idle AI podsOur platform was built for thousands of users and was serving 30 to 100 a day. I went through it service by service and cut what it reserved, while keeping live answers fast.
Jun – Oct 2026 · 5 monthsAI answers that are cheaper, better and configurable for every customer
$0.0012per answerI own the engine behind BHyve's AI answers, which searches a company's knowledge base and connected tools like SharePoint, Gmail and Outlook. This is how I made it cheaper per question, measurably more accurate, and configurable per customer without a fork.
Jun – Oct 2026 · 4 monthsMoving AI search from Postgres to LanceDB
5–6 msvector searchOur AI search ran inside Postgres, which scanned every chunk a user could see on every question. I moved it, in stages and without downtime, onto a dedicated vector store that keeps the same speed as the data grows and runs inside a customer's own cloud.
Jun 2025 – Sep 2026Document extraction, rebuilt and priced per page
40×faster Lite tierAI answers are only as good as the text we pull out of documents. I benchmarked the extraction engines, built a fusion pipeline that beats our old one on tables and headings, and turned it into three tiers each customer can pick by speed and cost.
Sep 2025 – Oct 2026From pentest report to fixes in a day
13 / 15findings fixedEnterprise customers buy security first. When a penetration test came back with 15 findings, I closed 13 of them the day after the test window ended. When a critical Next.js flaw was being used against our production website, I patched it while the attempts were still coming in.
May – Sep 2026Releases by tag, and a CI that costs a third
−71%CI minutesOne library change used to rebuild six apps. I redesigned how the monorepo builds and ships: merge to deploy, tag to release, and a CI that only builds what changed.
Apr – Oct 2026Leading a small team with reviews, a roadmap and AI pair-programmers
146PRs mergedOn a five-person team, leading means reviewing, unblocking and deciding what's next. I also built the tooling that lets each of us ship like a bigger team: AI agents with shared rules, and a loop from customer tickets straight to the board.
Jul 2025 – Oct 2026 · 15 monthsPlatform v2: one monorepo instead of thirteen repos
14 appsin one repoBHyve v1 was one frontend talking to twelve separate backend repos, each with its own chart and deploy. I started the new web app and became the largest contributor to Platform v2: one Nx monorepo with 14 apps, 24 shared libraries and one release process.
Nov 2024 – Feb 2026Owning the whole frontend for two years
97%of frontend commitsBefore Platform v2, I was effectively the only frontend engineer: the product, the marketing websites and everything customers clicked on. 671 of the 693 commits to the main app in that period were mine.
The last two years
Shipping, month by month.
My commits each month across 27 repositories. Highlighted months open the case study that started there.
Commits, November 2024 to October 2026
2,451 in total
2,476GitHub contributions in 2026, by late October
665GitHub contributions in 2025
2,019of my commits in the platform monorepo since Nov 2024
How I work
Five roles, one product.
Cost owner
I treat the cloud bill as a product metric. Shared AI compute, right-sized services, night-only workers and 85–92% smaller images, each measured before and after.
Team lead
One of four code owners on a five-person team. I've merged 146 pull requests into the platform and cut 59% of our production releases.
Roadmap planner
I wrote the BHyve AI v4 roadmap, and closed the loop from customers to the board: support tickets become Trello cards, and replies flow back.
Decision maker
I decide with data. A blind test on 935 real queries picked our embedding model. An A/B kept a caching trick switched off because it pushed give-ups from 50% to 84%.
Career
From hackathon winner to product engineer.
- 2017 – 2021 BE in Computer Science, GEC AurangabadJoint technical secretary, then technical secretary of the college.
- 2020 Founder, Zer070 Enterprise · Smart India Hackathon winnerMy first company, May to December 2020, and India's biggest student hackathon in the same year.
- Jun 2020 Web and app developer intern, N D InfotronicsRuby on Rails and Flutter, plus my first lessons in project management and APIs.
- Dec 2020 Web and app developer intern, BizoticsMumbai, until August 2021.
- Jan 2021 Software engineer intern, then developer, App MasteryIntern from January, software developer from August to November 2021.
- May 2021 Frontend developer, ArvolutionReact frontends, until May 2022.
- Sep 2021 Joined BHyveFull-stack engineer on a five-person team. Grew into the AI/ML work: extraction, retrieval and the answer engine.
- Today Product engineer and team lead, BHyveI own the AI answer engine, much of Platform v2, our release process, and a good part of what it all costs to run.
Tools I use most
Next.jsReactTypeScriptNestJSPythonFastAPIPostgreSQLLanceDBTurbopufferGeminiOpenAIKubernetesHelmArgoCDKEDAAzureGitHub ActionsClaude Code
Certifications
- Machine Learning for Everyone
- Statistical Thinking in Python (Part 1)
- Introduction to Python
- Python Data Science Toolbox (Part 2)
- Unsupervised Learning in Python
Winner, Smart India Hackathon 2020