Lead Engineer building enterprise .NET & AWS systems for 12+ years — now building the AI agents that run inside them.
C#, ASP.NET Core, Reactjs, AWS, Azure
Microsoft Agent Framework
Gurugram, India · Remote
a request moving through an agent — the shape I've been building in Microsoft Agent Framework
I've spent 12+ years as a backend and full-stack engineer, mostly on the .NET side — architecting microservices, leading teams, and shipping systems on AWS that businesses actually depend on. Lately I've been pointing that same engineering discipline at a newer problem: building AI agents that are reliable enough for production, not just a demo.
I'm currently a Lead Engineer at Teleperformance, working fully remote from Gurugram, India, and building out an AI-agent engineering practice on the side using Microsoft's Agent Framework — tool-calling, retrieval-augmented generation, multi-agent workflows, and the production discipline (tracing, evals, containerized deployment) that most tutorials skip.
Building enterprise-level applications for a global digital business-services provider, focused on operational efficiency and customer experience.
Technologies: C#, ASP.NET Core, .NET 7/8, AngularJS, SQL Server, GitHub CI/CD, Docker
Led development of mission-critical energy-monitoring applications on AWS, supporting solar production visualization and customer onboarding for a growing customer base.
Technologies: C#, .NET 7/8, ReactJS, SQL Server, MySQL, Entity Framework, LINQ, GitLab CI/CD, Docker, AWS EC2/EKS/S3, Quartz
Led development on Izenda's business-intelligence product, enabling data visualization and reporting on top of customers' existing databases.
Technologies: C#, ASP.NET Core, ReactJS, SQL Server, Entity Framework, LINQ, GitLab
Led modernization of FOXTONS, a legacy real-estate platform, onto current technologies and engineering practices.
Technologies: C#, ASP.NET Core MVC, JavaScript, SQL Server, Entity Framework, LINQ
Built result-processing applications for CSJM University Kanpur and Bundelkhand University, covering Medical, Para-Medical, Technical, and Regular academic programs.
Technologies: C#, ASP.NET, ADO.NET, MVC, WPF, JavaScript, SQL Server, Entity Framework, LINQ
A structured, phase-by-phase build covering the full AI agent lifecycle in .NET — from a raw LLM call to a production-shaped agent service — using Microsoft Agent Framework (MAF). Runs on the Gemini API via a community IChatClient adapter, so the whole build needs no Azure or OpenAI subscription.
DevWithAbhinavIChatClient.GetResponseAsync directly against Gemini with token-by-token streaming, before bringing in any framework, to understand the raw mechanics first.AIAgent instances with custom C# tool methods (function/tool calling), structured JSON output deserialized into typed C# records, and multi-turn history via MAF's session/thread abstraction./chat endpoint, with middleware logging every tool call and token count, and sessions persisted to SQLite so conversations survive a restart.TextSearchProvider context provider grounding answers in retrieved passages, with inline citations back to source documents.A Principal Architect's playbook for taking AI/LLM systems from discovery to steady-state operations — 7 phases, from feasibility and scoping through agentic orchestration, guardrails, LLMOps, and observability, closed out with a full capstone walkthrough.
A hybrid GenAI + Agentic AI reference — the exact tool for every step of a production system, from offline ingestion, vector indexing, and fine-tuning through runtime security, caching, retrieval orchestration, model serving, and post-execution guardrails and observability. 7 phases, 13 steps, 60+ tools mapped to when to reach for each.
Open to senior/lead remote roles and select freelance projects — especially where enterprise .NET meets AI agent engineering.