Software Engineer, AI · Princeton, NJ · Open to remote work or relocation

Akshant Jain

I build AI agents end to end, from design and evaluation to agents running in production.

I lead the BI analytics module and its AI agent at DataGOL, and I created Repolane, an open-source tool for running AI coding agents safely across repositories. Employee of the Year 2024.

  • 5 years of experience
  • Python
  • TypeScript
  • LangGraph
  • RAG
  • MCP
  • Agent evals
View ResumeSchedule a Call

Impact

4–6
engineers and testers led

Lead a team of 4–6 engineers and testers on DataGOL's BI analytics module and its AI agent.

2×
faster analytics AI agent

Made DAVE, the AI agent in DataGOL's BI module, 2× faster, nearly doubled its answer quality scores, and cut its errors by about two-thirds.

2–3×
faster client AI service, in 2 weeks

Guided a client's AI service to 2–3× faster responses within a 2-week deadline, by reviewing its pipelines, prompts and approach.

~10
parallel agent tasks with Repolane

Built Repolane, an open-source tool that runs about 10 AI coding agent tasks in parallel across 5–6 repositories, each in its own isolated worktree.

About

Portrait of Akshant Jain
Akshant Jain
Software Engineer, AI
Open to opportunities

My focus is the engineering around the model: agent workflows, evaluation, and the reliability, latency and cost work that makes agents dependable in production. I started as a front-end engineer and grew into full-stack and AI work over five years, picking up team leadership and mentoring along the way, and studied Computer Science with a minor in Mathematics at the University of Illinois at Chicago.

Writing

Experience

  1. Software Engineer · BI Analytics Lead

    InnCreTech LLC
    Oct 2023 — Present

    DataGOL

    InnCreTech's AI-native data and agents platform (warehouse, ETL, lineage, BI, multi-agent orchestration and governance). I own and lead its BI analytics module and DAVE, the module's AI analytics agent.

    • Own DAVE, the BI module's AI analytics agent: it turns a question into database queries, finds trends and anomalies, and builds charts, widgets and reports, with tool-call and config validation that double-checks its answers against the real chart data.
    • Led improvements to DAVE that raised its evaluation scores by ~80%, made it 2× faster and cut errors and invalid configs by about two-thirds.
    • Built its Playwright-based evaluation framework (rendered charts and widgets plus content checks) and ran experiments across frontier and open models.
    • Own the BI analytics module end to end, including its system design (query layer, object-oriented design, data structures, latency) and its AI agent, and lead a team of 4–6 engineers and testers.
    • Client-facing, forward-deployed work: weekly syncs with clients to gather requirements, walk through trade-offs and progress, and run demos; turn business needs into specs with product and stakeholders.
    • Advised on a client's AI service under a 2-week deadline: reviewed its pipelines, prompts and approach, and guided changes for 2–3x lower latency and leaner, cheaper prompts, plus next features like memory and alerts.
    • Built AI features on OpenAI that let users ask in plain English and get charts and insights, cutting manual analysis work by ~90%, then rebuilt them as a layered BI agent (transformation, classification, visualization and configuration layers) on a shared transformation layer, so manual and AI-generated analytics use one format.
    • Architected the dashboard engine (drill-down, conditional formatting, optimized SQL, in-memory caching, parallel queries) for sub-second responses on large datasets, and hardened the module's performance and security.
    • Built a white-label dashboard embedding framework with theming and API-based configuration, a reporting engine with ad-hoc queries and PDF/Excel/CSV export, and event-driven threshold alerts.
    • Built data querying over JDBC and Spark and a search interface that lets non-technical users explore their data.

    Private Capital Deal Platform

    SaaS platform for private debt capital markets. As my focus moved to DataGOL, I took on a lead and mentor role here.

    • Built an AI document feature that turns uploaded financial documents into structured financial data and lets users ask plain-English questions about the extracted results.
    • Mentor newly hired engineers through onboarding and code reviews, and run technical interviews for engineering candidates.

  2. Programmer Analyst

    InnCreTech LLC
    Oct 2021 — Sep 2023

    Private Capital Deal Platform

    SaaS platform for private debt capital markets and deal processes, connecting private equity sponsors, lenders and advisors.

    • Migrated the platform from AngularJS to React, cutting API calls by 65% and page load time by 55%.
    • Built REST APIs handling 1M+ calls a day at 99.95% uptime, plus secure deal rooms for sponsors, lenders and advisors (encryption, role-based access, audit logs, SOC 2), an NDA layer for confidential deal information and a coverage module with the full history of lender–sponsor interactions.
    • Served on the production monitoring rotation, fixing ~10 production bugs and shipping ~5 patches per month.

    Additive Manufacturing Platform

    Jan 2023 — Sep 2023

    Material management for an additive manufacturing platform.

    • Improved material control, planning and flow across manufacturing facilities and integrated automated calculations into the platform, cutting errors by 50% and manual effort by 95% and speeding up the process by 25%.
    • Built a library of reusable React components for the platform's new React front end, and owned delivery end to end: requirements, specs, coding, testing, deployment, user training and support.

  3. Software Developer (Part-time)

    Stealth Startup
    Jul 2021 — Sep 2021
    • Designed and built the startup's customer-facing landing website for its product launch, plus front-end prototypes of popular existing sites for its testing phase.

  4. Web Developer (Intern) · New Delhi, India

    SVS Techno Consultants Pvt. Ltd.
    Jun 2020 — Aug 2020
    • Turned the company's website into a React and MySQL dashboard with Firebase authentication and two-step sign-in, improving progress updates between employers and administration by 25%.
    • Built and tested a Node.js email API with SendGrid, optimized performance with a caching system, and wrote testing scripts, working in the web team's Scrum workflow.

Projects

Repolane

Problem
Running several AI coding agents across many repositories at once leads to conflicting changes, mixed-up context, and agents straying outside their task into secrets, other repos or main branches.
Solution
An open-source (Apache 2.0) tool that gives each task its own git worktree and checks every agent action with a rules engine on Claude Code hooks, so agents can work in parallel safely. Designed for running many tasks in parallel: about 10 at once across 5–6 repositories, each in its own isolated worktree.
WebsiteGitHub
PythonBashGitClaude CodeAI agents
The Repolane board: three active lanes and one parked, across five repos, with per-repo uncommitted and unpushed counts.The Repolane board: three active lanes and one parked, across five repos, with per-repo uncommitted and unpushed counts.
  1. 01WorkspacesGit worktree per task, one clone per repo
  2. 02Rules engineClaude Code hooks check every agent action
  3. 03Regression suite184 automated cases plus live self-checks
  4. 04Memory & boardScoped agent memory, local dashboard
  • Designed a workspace model on git worktrees (one clone per repo, one isolated workspace per task) so several AI coding agents can work in parallel across repos without conflicts or mixed-up context.
  • Built a Python rules engine on Claude Code hooks that checks every agent action, including shell command chains and resolved file paths, to keep agents in scope, block access to secrets and protect main branches.
Read the full case study

Earlier projects

Show 6 college and early projectsHide

Cloudgile

Jan — May 2021

Agile project management web app built by a four-person team using Scrum: issues, sprints, backlog, chat and project history, with users and data allocated by project role.

ReactMaterial UIFirebaseJavaScript

My Daily Life

Aug — Dec 2020

Working prototype of a planner that brings a daily schedule, goals and checklists into one interactive overview, designed on UI principles in a five-person team.

ReactHTMLCSSNetlifyUI design

Recognition & education

Award · 2024

Employee of the Year

InnCreTech LLC

For leading the BI analytics module and its contribution to winning new customers.

Education · 2021

University of Illinois at Chicago

BS Computer Science, Mathematics minor

Dean's List (Fall 2019, Spring 2021) · ACM member (ACM UIC, SIG-WebDev)

Certifications
Show 3 Google Cloud certificationsHide

Recommendations from colleagues are on LinkedIn

Skills

Agent toolset

AI & agents
Multi-agent systemsAgent harnessesAgentic workflowsTool callingContext engineeringAgent evaluationRAGHybrid search (BM25 + embeddings)Vector searchHuman-in-the-loopLLM observability & cost trackingPrompt engineeringMCP
LLMs & frameworks
LangGraphLangChainClaudeOpenAIGeminiEmbeddings
AI dev tools
Claude Code (hooks, skills)CursorGitHub Actions

Engineering foundation

Languages
Python · TypeScript · JavaScript · Java · SQL
Frameworks
FastAPI · Next.js · React · Node.js · Spring Boot · SQLAlchemy · Pydantic
Data & cloud
PostgreSQL · Spark SQL · Redis (Streams, pub/sub) · Weaviate · DuckDB · Docker · Kubernetes · GCP · CI/CD
Testing & security
Playwright · OAuth 2.0 / PKCE · JWT · Role-based access control (RBAC) · Multi-tenant isolation · Sandboxed code execution
Portrait of Akshant Jain
Open to opportunities

Building AI agents? Let's talk.

I'm looking for AI engineer roles where I can build agent systems end to end. Book a call or grab my resume, and I'll get back to you quickly.

View ResumeSchedule a Call