16+ yrs, Hyderabad, India (IST). Immediately available; open to in-office, hybrid, or remote roles from Hyderabad
Abhishek Maurya▍
Staff Software Engineer — AI agent platforms (MCP, evals) and front-end platform delivery in React/TypeScript, Python/Java
Results
What I do
Eight areas, from agent platforms to backend ownership. Expand a tile for the short version.
Agentic AI & MCP
Designed and shipped MCP-driven agentic workflows integrated into the engineering lifecycle, adopted by 20+ teams with roughly 95% less research and debugging effort.
Local LLM inference
Run MLX-optimized models (Qwen, Gemma, DeepSeek) locally on Apple silicon via Ollama, plus memory-efficient loaders like turbo-fieldfare that stream model portions on demand: Gemma 4 26B under 2GB RAM. Took VLMs end-to-end on-device: Qwen2-VL-2B on llama.cpp/GGUF via Metal across a quantization ladder on iPhone, with sub-second TTFT from architecture and resolution levers.
Developer platforms
Founded the Agentic Developer Platform: multi-team bootstrap and governance infrastructure for agents, skills, and MCP servers.
Frontend architecture
Architected scalable React and TypeScript systems powering low-code tools like Table Builder and Workspace Builder.
Backend & data ownership
Hands-on backend behind the surfaces: Python/FastAPI and SQLite services with guarded, read-only SQL access, plus Java/Glide enterprise case backends and REST APIs.
System design
Metadata-aware, multi-model architectures and design patterns built to hold up across teams, tenants, and releases.
Quality & reliability
Enterprise testing strategy with Jest, React Testing Library, and Playwright; performance optimization and WCAG/ARIA accessibility. Lifted legacy coverage from 20% to 90%.
Technical leadership
Lead a 9-person engineering team, run technical hiring and high-bar architectural reviews, and mentor engineers in AI-first development practices.
Selected work
Three shipped agent systems. Each one has a deep dive.
Agentic Developer Platform (ADP)
Multi-team bootstrap and governance infrastructure for Claude Code, MCP servers, agents, and skills. Built in four weeks on a multi-agent orchestration pattern, rolled out to 7 pilot squads across 20+ teams with 20+ skills and 20+ agents.
MCP-driven engineering workflows
Integrated MCP-driven agentic workflows into the engineering lifecycle organization-wide. Reduced research and debugging effort by approximately 95% while improving accuracy.
Build Agent, ServiceNow Studio
Elevated App Engine with agentic workflows for AI-assisted application creation, flow generation, and tool orchestration across 35+ metadata types and 11 domains. Built on the planning pattern (think first, then execute) with a metadata-aware, multi-model (Claude default; Now LLM + Claude on Bedrock), self-healing agentic architecture.
Selected builds
Side projects, shipped and living online.
SpendIQ Copilot
Conversational spend-analysis agent: LangGraph ReAct over SQLite + FTS5 with SQL guardrails (SELECT-only, read-only connections), an AST-whitelisted calculator instead of eval, and a 14-case golden-set eval harness with majority voting, all passing
Visit SpendIQ Copilot →ordo
On-device vision-language model built on Qwen2-VL-2B with llama.cpp across a GGUF quantization ladder, deployed to iPhone (A16), with a private photo eval set, per-stage TTFT decomposition, and LoRA accuracy recovery
Visit ordo →
Revision
Local-first Tauri desktop app for principal-level interview prep: FSRS-5 spaced repetition, drag & air gestures, single SQLite file, fully offline. DSA / system design / AI / behavioral decks with glassmorphic review, cloze + KaTeX, and 53-week analytics
Visit Revision →
Switchyard
Interactive simulator for an agentic AI + RAG pipeline: watch ingestion, retrieval, tool calls, memory, and a live trace of every internal step while the loop runs.
Visit Switchyard →jev-browser
Harness-agnostic TypeScript core that puts Jev (TypeSafe System One) in charge of browser decisions: one observed element and one operation per step, text-only payloads with no screenshots in the loop, zero runtime dependencies
Visit jev-browser →job-search-skills
Two portable agent skills that run an entire job search locally: job-finder sweeps boards and ranks roles by real eligibility, apply-to-jobs autofills and submits ATS applications in your own browser, and a Jev decision layer keeps uncertain answers uncertain
Visit job-search-skills →Experience
16+ years across AI platforms, frontend, backend and founding teams.