Distributed Systems · Ad-Tech · AI Deployment
Swapnanil Saha
Nine years building the infrastructure behind real-time digital advertising. Now bringing that same systems discipline to enterprise AI.
Ad Filtering Latency — Custom Redis Module · C
200
ms
↓ 5× reduction · significant QPS gains · built independently
Years in Production Systems
9
Media.net · Ad-Tech
Internal AI tools shipped
3
SERP · Wiki · Campaign agent
Daily ad requests
B+
Serving infra · end-to-end
Auction types engineered
2
First-price · Second-price
About
Systems depth.
Business clarity.
I've spent 9 years inside the engine room of real-time digital advertising — building infrastructure that decides, in milliseconds, which ad a user sees. From a custom Redis module that cut filtering latency 5×, to auction strategy systems that directly moved advertiser budgets, to real-time budget pacing on Cassandra across billions of daily requests.
What makes my work unusual is that I've never been able to hide behind pure engineering. Ad-tech has immediate, measurable outcomes — every latency improvement has a win-rate implication, every auction strategy change has a revenue footprint. Connecting technical decisions to business results is a discipline I've been building for a decade.
I also quietly became the person who shipped internal AI tooling at Media.net before it was fashionable — a SERP template generator, a Slack-integrated docs wiki, and a campaign agent that can pause underperforming campaigns autonomously. Each one started from a business problem, not a technology impulse. That's the pattern I intend to keep.
Current role
Lead SDE · Media.net
Location
Mumbai, India
Primary domain
Ad-Tech · Real-Time Systems
Building toward
Enterprise AI Deployment
Education
B.E. CS · BIT Mesra
Founder instinct
2 startups built · 2015–16
Experience
Nine years.
One company.
Real-time financial infrastructure + three internal AI tools shipped
Two parallel tracks at the Lead level — one solving the hardest distributed consistency problem in ad-tech, one establishing the LLM practice at Media.net from scratch.
Business Problem
Ad campaigns must pace spend accurately across thousands of real-time auctions per second. Underspend wastes advertiser budget; overspend creates financial liability. In a distributed system, maintaining a consistent, real-time view of "how much has been spent" while sustaining the write throughput that RTB demands is a fundamentally hard problem — and getting it wrong is immediately visible in the P&L.
Engineering Solution
Architected real-time budget pacing infrastructure on Apache Cassandra — engineered for financial precision under distributed consistency constraints. Designed the state synchronisation layer that keeps budget counters accurate across geographically distributed nodes without sacrificing the write throughput that real-time bidding demands. Correctness is non-negotiable; the system either works exactly right, or advertisers notice immediately.
On the AI front, shipped three internal tools — each starting from an identified business pain:
Auto SERP Template Generator — eliminated hours of manual ad template creation. Became the most-used AI tool companywide. The first proof that LLM deployment inside Media.net was worth investing in.
Docs Wiki · Slack Integration — made internal knowledge accessible via natural language through Slack webhooks. Reduced time-to-answer on process and technical questions that previously required pinging specific people.
Campaign QnA Agent — a conversational assistant that goes beyond answering questions. It can take minor actions autonomously — including pausing underperforming campaigns — making it the first agentic tool in the company's stack.
Auto SERP Template Generator — eliminated hours of manual ad template creation. Became the most-used AI tool companywide. The first proof that LLM deployment inside Media.net was worth investing in.
Docs Wiki · Slack Integration — made internal knowledge accessible via natural language through Slack webhooks. Reduced time-to-answer on process and technical questions that previously required pinging specific people.
Campaign QnA Agent — a conversational assistant that goes beyond answering questions. It can take minor actions autonomously — including pausing underperforming campaigns — making it the first agentic tool in the company's stack.
Auction strategy systems — engineering market mechanisms that move money
Business Problem
The digital advertising market was mid-transition from second-price to first-price auctions — a fundamental market-structure shift changing how advertisers bid and how publishers yield. Media.net needed to correctly implement both mechanisms and ship bid shading logic that protected advertiser ROI while preserving publisher yield. Get the balance wrong and advertiser budgets migrate to competing exchanges within days.
Engineering Solution
Designed and shipped first-price and second-price auction engines plus competitive pricing and bid shading logic — navigating the inherent tension between supply-side and demand-side incentives in a real-time marketplace. Built simulation tooling to evaluate pricing strategy changes pre-deployment, enabling data-driven decisions with quantifiable revenue impact before touching production traffic.
Auction strategy changes have direct, immediate revenue footprints — this is engineering where every decision is visible in the P&L within hours. Operated at the intersection of market economics, systems engineering, and business strategy; translated partner feedback and market signals into algorithm changes with measurable outcome metrics.
Conversion tracking SDK — developer experience as a direct lever on business outcomes
Business Problem
Advertisers couldn't reliably measure whether users who clicked their ads went on to convert — buy, sign up, complete a form. The existing pixel was brittle and frequently misimplemented, producing noisy conversion signals that made CPA bidding unreliable. Without clean conversion data, the entire bidding optimisation stack is operating on bad inputs. This was limiting budget growth from performance advertisers who need to prove ROI.
Engineering Solution
Redesigned the conversion tracking pixel JavaScript SDK from scratch — prioritising correct implementation by default and minimal integration friction. Achieved rapid, complete adoption across the full advertiser base. Accurate CPA measurement fed downstream bidding optimisation, producing measurable improvement in cost-per-acquisition efficiency and directly increasing advertiser budget commitment on the platform.
Owned the full lifecycle of a customer-facing technical artifact: requirement scoping → implementation → cross-functional coordination with business and account teams → rollout → post-launch measurement. The same end-to-end ownership pattern that defines every successful enterprise AI deployment — just an earlier iteration of it.
The Redis module — 200ms → 40ms, written in C, independently
Independently engineered a custom Redis module in C that reduced ad filtering response latency from ~200ms to ~40ms — a 5× improvement — while sustaining significant QPS gains. This directly enabled tighter real-time bidding windows and improved win rates for downstream auction systems. Also owned reliability and observability of the serving infrastructure handling billions of daily ad requests, maintaining sub-SLA latency targets across distributed components and transitioning the team from reactive incident response to proactive system ownership.
Earlier · Startup Experience · 2015–2016
India's most downloaded shopping extension — early-stage product engineering
Contributed to Flipshope during its early growth phase — a browser extension that solves a genuine consumer problem: detecting real discounts versus manufactured price inflation, and automatically applying the best coupon at checkout. The product went on to become the most downloaded shopping Chrome extension in India, with 5L+ extension installs, 10L+ app downloads, and a 4.5+ rating on the Chrome Web Store across 300+ supported brands. Worked in a bootstrapped, founder-led team where shipping fast and shipping right were the same thing.
First venture — zero to live product as a student
Founded and built Ransphire while still in college — going from idea to a live product entirely independently. The experience of identifying a problem, building a solution without a playbook, and putting it in front of real users planted a business instinct that has quietly shaped how I approach engineering problems ever since. The company didn't scale. The education was irreplaceable — and it's part of why I think about technical work the way I do.
Skills
What I
bring.
Systems · Infrastructure
Distributed Systems Design
Redis · Custom Modules (C)
Apache Cassandra
Real-Time Data Pipelines
High-Throughput Ad Serving
Observability · SRE
AI · LLM Deployment
LLM Application Development
RAG Pipelines
LangChain · LangGraph
MCP Server Development
Eval Frameworks (RAGAS)
Agentic Workflows · Actions
Domain · Business
Real-Time Bidding (RTB)
Auction Mechanisms (1st/2nd)
Ad Serving Architecture
CPA / Conversion Tracking
Python · JavaScript · C
Founder Mindset
llm-tools suite
Six tools.
Shipped.
Six production-grade CLI + REST API tools — each solving a real enterprise problem with Claude. Built independently, in public, to the same standard I'd apply to internal tooling at scale. Each has Docker, FastAPI, Pydantic validation, a test suite, and a full landing page.
Ad Tech · Creative AI
ad-copy-critic
Scores ad copy across 8 dimensions with specific fixes and rewrite variants. Performance feedback loop tracks which dimensions predict real CTR. Competitor gap analysis, brand voice compliance, localisation readiness, and Slack-ready summaries.
Ad Tech · Diagnosis · Alerting · Ops
campaign-health
Expert diagnosis of ad campaign metrics with root causes ordered by severity. Custom alert rules trigger on threshold breaches. Budget pacing projects burnout risk before it happens. Vertical-specific benchmarks (ecomm, fintech, gaming, travel) replace one-size-fits-all thresholds. Recommendation prioritiser extracts quick wins. Weekly digest summarises the fleet for clients.
AI Architecture · RAG
rag-readiness
Opinionated architecture recommendation per component. Diagnoses existing broken stacks with root causes by severity. Rule-based cost estimation, iterative refinement with session persistence, and RAGAS eval dataset generation.
LLM · Evaluation · Regression · CI/CD
llm-eval-suite
Evidence-backed multi-dimensional scoring across 10 task types including RAGAS-compatible RAG eval. Regression testing saves baselines and blocks CI when scores drop. Claim-level hallucination detection, prompt sensitivity analysis across variants, and multi-judge panel consensus with disagreement flagging.
Enterprise AI · Strategy · LangGraph
ai-use-case-scoper
Hybrid 8-question flow with optional Graph RAG doc enrichment — pre-fills tech context, always asks qualitative questions. LangGraph check-in pipeline evolves plans. Company memory persists across sessions.
Productivity · Meeting AI
meeting-to-action
Normalizes Zoom/Teams/Meet transcripts, detects meeting type, extracts structured decisions and action items. Cross-meeting commitment tracker flags missed items by severity. Weekly digest aggregates open work by owner across all sessions.
Now
What I'm
building.
Active — IBM RAG and Agentic AI Specialisation · 10 courses
Systematically building production AI deployment expertise
Covering RAG pipelines, vector databases, multi-agent orchestration with LangGraph and CrewAI, MCP server development, and agentic AI patterns. Every module feeds directly into real projects.
Courses 1–5
✓
Course 6
10%
Courses 7–10
—
Project in progress
Ad Campaign Intelligence Agent
A LangGraph agent that reads campaign performance data via a custom MCP server, answers natural language questions over a RAG-backed knowledge base, and is evaluated with RAGAS for production readiness. All three skill areas — agents, RAG, MCP — in one coherent project built on real domain knowledge.
Long game
From deployment to ownership
The trajectory I'm building: deep AI deployment expertise → strategic consulting → eventually a practice or venture of my own. The same instinct that led me to build Ransphire in college, now backed by a decade of production systems experience.
Contact
Let's
talk.
If you're working at the intersection of production systems and enterprise AI — or if something here sparked a conversation worth having — I'm always open to a good discussion.
"The Redis module wasn't assigned to me. I saw the latency number, understood what it meant for win rates, and built the fix."
— How I approach every problem