Abhishek Sharma
Open to work2 years experienceAI Engineer
AI Engineer specializing in autonomous agent systems and voice AI infrastructure.
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
50 skillsWork Experience
AI Engineer
IBR Infotech
- Architected Pushable AI, a multi-tenant AI agent platform with per-user Docker isolation, LangGraph orchestration, browser automation (Chrome + Steel.dev), and 250+ app integrations via Composio.
- Solo-built a production-grade VAPI-alternative voice platform on OpenAI Realtime API + Twilio — sub-1s latency, speech interruption handling, dynamic tool calling, and an admin panel for agent configuration.
- Built and deployed 100+ production voice calling agents across VAPI, Retell AI, Bland AI, and Synthflow using advanced prompt engineering, RAG, and webhook integrations.
- Built an Asana Intelligence Agent using LangGraph + pgvector that dynamically queries Asana APIs to answer natural-language questions about team productivity across 30 employees.
- Developed a Slack×Claude Code integration that triggers autonomous multi-agent coding workflows (frontend, backend, DB, tester) from Slack instructions, with Slack-based status reporting.
- Implemented CI/CD pipelines on GitHub Actions, Jenkins, AWS EC2, ECR, and CodeBuild for all AI services.
Projects
Pushable AI
- Multi-tenant agent platform — per-user Docker isolation, dual-layer memory (pgvector+SQLite), task scheduling, browser automation, and 250+ app integrations.
- 8-service Docker stack with ~50 PostgreSQL tables, a ~2,500-line LangGraph state machine driving tool dispatch + human-in-the-loop approval + summarization, and BullMQ workers on Redis.
ClawGen
- AI agent with 17 tools that scaffolds complete OpenClaw projects from a one-line description; live React Flow architecture diagram updates in real time as files are written.
- Human-in-the-loop MCQ tool calling on the Vercel AI SDK, sandboxed bash execution with path-traversal guards, full tool-call replay from SQLite, and provider-agnostic LLM gateway (OpenAI / OpenRouter / Groq / Ollama).
Vox Assist
- Self-hosted VAPI alternative — Twilio Media Streams↔OpenAI Realtime bridge (gpt-4o-mini-realtime) with sub-1s latency, browser test interface, and configurable HTTP tools exposed as OpenAI function calls.
- Live transcript/event WebSocket, Supabase auth + Postgres for assistants / tools / call history, and Docker Compose deployment.
Loom AI
- Encrypted “memory card” SaaS — per-user end-to-end encrypted notes, files, and reminders; AI assistant recalls memories on demand and executes scheduled actions on Gmail / Slack / Notion / Google Calendar via Supabase Edge Functions.
- OAuth-driven integrations, Lemonsqueezy plan gating, and cron-based action runner.
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Achievements Not Earned
Special rewards, developer badges, system recognition certificates, and conceptual milestones will display here.
About Details
Professional Bio
AI Engineer with 2 years of experience building autonomous agent systems, voice AI infrastructure, and multi-agent platforms. Specialized in LangGraph orchestration, RAG pipelines, OpenAI Realtime API, and LLM tool/function calling.
B.Tech in Information Technology
Malwa Institute of Science & Technology (2022 - 2026)