FasterOutcomes · Legal technology
Legal AI platform
Document ingestion, citation-backed research, and draft generation connected through durable workflows and attorney review.
LangGraph / Temporal / Python / Elasticsearch
Read about the workI build the infrastructure
underneath AI products.
8+ years building retrieval that can be audited, agents that survive a restart, and systems people can depend on.

Selected work
All of them clone and run green with no API key — the offline providers are real implementations, not mocks.
agentic-rag-platform
Hybrid BM25 and dense retrieval fused by reciprocal rank, with a loop that re-queries when the retrieved context cannot answer the question. The published eval table shows hybrid losing to plain BM25 — left in, with the reason, rather than tuned until it flattered the architecture.
llm-gateway-router
Cost-estimated and latency-aware routing across providers, per-provider circuit breakers, response caching with near-duplicate matching, and per-tenant spend attribution. Zero dependencies, static binary in a scratch image, every test under the race detector.
agent-orchestrator
A run is an append-only event log and state is a pure fold over it, so a run paused for human approval resumes in a different process entirely. CI asserts that property on every push.
llm-eval-harness
Wilson confidence intervals and McNemar's exact test, because on a 50-case suite a six-point accuracy drop is indistinguishable from a coin flip — and a gate that fails on noise gets deleted within a fortnight.
realtime-voice-agent
Full-duplex streaming speech to model to speech. Interrupting stops the audio, cancels generation, and truncates conversation history to what the caller actually heard — the third part has no symptom in a single-turn demo, which is why it ships broken.
Focused tools
llm-guardrails
Luhn and Verhoeff checksums, so a 16-digit order reference is not reported as a credit card. Includes Aadhaar and PAN, which Western tooling omits and Indian product data is full of.
text2sql-agent
A statement is rejected unless it is recognisably a read. Repair is driven by the real database error, because a generic failure message just gets the same guess back.
prompt-registry
Content-addressed versions and sticky A/B assignment with no shared state, so a user does not get a different personality on their second message.
llm-batch-processor
fsynced checkpoints and exact resume across 100k-item batches, with a cost estimate before the run rather than an invoice after it.
embedding-benchmark
Because a model two points better at four times the price is the wrong choice, and an index eight times larger is eight times the bill forever. Matryoshka truncation is measured, not assumed.
doc-intelligence
Every extracted field carries the character span it came from, so “why does the system think this invoice is £3,720” has an answer that is a line number, not a shrug.
mcp-server-toolkit
JSON-RPC from scratch against the 2026-07-28 spec, plus a 14-check conformance report covering what actually breaks interoperability — starting with notifications that must never be answered.
kafka-llm-pipeline
At-least-once delivery with effectively-once cost, via a content-keyed dedup store. Poison messages leave the partition instead of blocking everything behind them.
streaming-chat-ui
A stream yields arbitrary byte chunks, not messages. Tested one byte at a time, split across CRLF, and split through a multi-byte UTF-8 character — the cases that work on localhost and drop tokens in production.
lora-toolkit
Gradients checked against finite differences and trained adapters measured against the Eckart–Young floor, landing within 0.0008 of the theoretical optimum.
Beyond my own repositories
Contributing to the tools other engineers build with, from React components and AI interfaces to monitoring and documentation.
7 selected merged pull requests · 6 upstream projects
Notify consumers when selection overlay rectangles are removed.
Migrate the select component to a function component.
Improve handling of HTTP failures in the PagerDuty v1 integration.
Normalize language links across the documentation.
Keep the model selection on questionnaire follow-up requests.
Migrate the file picker from a class to a function component.
Correct README typos and formatting.
Industry work
FasterOutcomes · Legal technology
Document ingestion, citation-backed research, and draft generation connected through durable workflows and attorney review.
LangGraph / Temporal / Python / Elasticsearch
Read about the workIBM Labs · Enterprise platforms
Event ingestion, predictive services, and interactive dashboards supported by metrics, logs, and distributed tracing.
Kafka / FastAPI / React / OpenTelemetry
Read about the workTesco · Through Publicis Sapient
Regional grocery experiences across the UK, Central Europe, and APAC, with delivery integrations and independently deployable frontends.
React / Micro frontends / Kafka / Webpack
Read about the workFitbots · Founding team
Goal tracking, performance insights, and HR workflows supported by a reusable component library and accessible interfaces.
React / Next.js / Stencil / Tailwind
Read about the workExperience
Both ends of the range: deciding what to build with nothing in place, and shipping inside systems that already carry real traffic.
Senior Agentic Systems Developer
Agentic systems for a communications platform.
Lead Engineer, GenAI · founding team
Legal document ingestion, semantic search, drafting, and human review, orchestrated with LangGraph and Temporal.
Senior Full-Stack / AI Engineer
Customer analytics, event pipelines, and observability dashboards. Microservices, predictive features, and cross-functional engineering mentorship.
Senior Software Engineer
Tesco grocery experiences across UK, CEU, and APAC: maps and delivery integrations, micro frontends, and enterprise identity tools.
Founding Engineer
Employee OKR SaaS: goal tracking, HR workflows, and a reusable component library built with accessibility in mind.
Stack
A little more about me
My work spans web products, AI workflows, and the platforms that keep them running. I bring that full-stack perspective to retrieval, automation, and developer tools.
Agents, retrieval, document intelligence, and workflows with human review.
Accessible interfaces, reusable components, and APIs that connect products to their data.
Cloud delivery, event pipelines, observability, and engineering mentorship.
2017–2019
Jain University, Bangalore
Gold medalist · GPA 9.1/10
2014–2017
Bhagwan Mahavir College, Surat
GPA 8.9/10
Jain University
Recognition for academic achievement during my MCA.
IBM
Appreciation for contributions to the team.
Tesco
Recognition for work on customer experiences.
Notes from building
Evaluations
Build a small, useful evaluation suite around outcomes, forbidden actions, and realistic failures.
Read articleAgent reliability
A practical design for agent retries, durable state, and duplicate prevention, using a customer refund workflow.
Read articleContext engineering
How to build a useful context packet for an AI support agent without losing customer commitments or exposing unrelated data.
Read articleHave something in mind?
AI infrastructure, agentic systems, and software built to last. Let’s talk about what you’re building.
Send me an emailOr reach me on LinkedIn