Associate Staff AI Engineer / Nagarro Software

Building AI Systems That Ship

>>> AGENTIC SYSTEMS · ARCHITECTURE TO PRODUCTION TRAFFIC

I take agentic systems from architecture to production traffic. Four years of multi-agent orchestration, RAG, and MCP tooling across retail, e-commerce, voice, and vision surfaces - built for extensibility, so new capability ships by configuration rather than redeployment.

Multi-Agent SystemsConversational AIRAGMCP & Agent SkillsVoice AgentsContext EngineeringGuardrailsAgentic-Commerce

$ sec.01 / career

Career

Four roles at Nagarro since 2022. The work itself is below.

Career progression at Nagarro Software, most recent first
RECROLELEVELPERIODDUR
04
Associate Staff AI EngineerCURRENT

Own the architecture of a multi-tenant agent platform, and lead engineering enablement on AI in the SDLC.

  • Set the architecture for one agent runtime serving web chat, WhatsApp and voice
  • Made capability additive - new brands, regions and tools land as configuration, not deployments
  • Put prompt, model and flow control in product hands, with tracing to keep it accountable
  • LangGraph
  • LiteLLM
  • FastAPI
  • OpenAPI
  • Distributed Tracing

Nagarro Software · Indore, India

StaffJul 2026 – Present1M
03
Senior AI Engineer

Led AI delivery end to end - document intelligence, computer vision, process automation - and took on RBAC and data governance for SOC 2.

  • Took extraction accuracy from demo-grade to 90%+ against live transaction volume
  • Cut manual workflow handling by 40% for 500+ enterprise users
  • Introduced RBAC and data governance controls ahead of SOC 2
  • LangGraph
  • AWS Textract
  • OpenCV
  • DLib
  • Camunda BPM
  • RBAC

Nagarro Software · Indore, India

SeniorFeb 2025 – Jul 20261Y 5M
02
AI Engineer

Built the first production agent systems on Google ADK and Vertex AI, across chat, voice, and document surfaces.

  • Shipped the team's first agent systems into production, not prototypes
  • Built retrieval that cites its sources, in two languages, at 300ms
  • Extended a single order pipeline across both voice and document intake
  • Google ADK
  • Gemini
  • Vertex AI Search
  • Firestore
  • Cloud Run

Nagarro Software · Indore, India

MidJul 2023 – Feb 20251Y 7M
01
Associate Engineer

Real-time platform engineering - streaming, WebSockets, and microservices at concurrent scale.

  • Held 1,000+ concurrent viewers at sub-second latency on live video commerce
  • Socket and REST infrastructure spanning 50+ microservices
  • AWS IVS
  • WebSockets
  • React
  • Node.js
  • DynamoDB

Nagarro Software · Gurugram, India

JuniorFeb 2022 – Jul 20231Y 5M

$ sec.02 / selected_work

Selected Work

Seven systems shipped to production. Each one names the role it was built in.

  1. Three-tier agent orchestration - a central planner, seven domain subagents, and parallel ReAct workers on LangGraph - serving web chat, WhatsApp, and voice.

    Workers run in parallel, so added capability does not accumulate serial latency. Zero-code multitenancy through a four-level configuration hierarchy (Global → Brand → Region → Persona) onboards new brands and regions without a deployment, with a model-agnostic LiteLLM gateway routing per tenant. Backend endpoints become agent tools automatically from their OpenAPI specs, annotated with workflow-chaining metadata so the planner can compose multi-step flows against endpoints it has never seen. Persistent semantic memory with a consolidation layer carries personalisation across sessions, a 14-tab admin console puts prompt, model, and flow control in non-engineers’ hands, and distributed tracing attributes latency and token cost per agent node.

    7 domain subagents · parallel workers · new brands ship by config alone

    • LangGraph
    • LiteLLM
    • ReAct Agents
    • Agent Memory
    • OpenAPI
    • FastAPI
    • Distributed Tracing

$ sec.03 / skills

Skills

  • Proficiency:
  • Expert
  • Advanced
  • Intermediate
AI/ML & Agents12 ENTRIES
  • Multi-Agent Systems
  • LangGraph
  • LangChain
  • Google ADK
  • RAG
  • Context Engineering
  • Function Calling
  • MCP Servers
  • Agent Skills
  • Agent Memory
  • LiteLLM
  • Knowledge Graphs
Conversational & Voice6 ENTRIES
  • Conversational AI
  • Voice Agents
  • Speech-to-Text
  • Intent Routing
  • Multi-Turn Memory
  • Multilingual NLU
GenAI & LLMs8 ENTRIES
  • Claude API
  • Gemini API
  • OpenAI SDK
  • Structured Outputs
  • Streaming
  • Prompt Caching
  • Guardrails
  • HF Transformers
AI Systems Engineering6 ENTRIES
  • LLM Observability
  • Distributed Tracing
  • Token Cost Optimisation
  • Model Routing
  • Multi-Tenant AI
  • RBAC & Governance
Computer Vision7 ENTRIES
  • OpenCV
  • DLib
  • OCR (Textract)
  • PyTorch
  • TensorFlow
  • scikit-learn
  • Visual Search
Backend8 ENTRIES
  • FastAPI
  • Python
  • REST
  • Node.js
  • Express.js
  • WebSockets
  • Microservices
  • Event-Driven
Frontend4 ENTRIES
  • React.js
  • Next.js
  • TypeScript
  • Tailwind CSS
Cloud6 ENTRIES
  • GCP
  • AWS
  • Vertex AI
  • Cloud Run
  • Lambda
  • AWS IVS
Data & Storage8 ENTRIES
  • Qdrant
  • Vertex AI Search
  • Hybrid Search
  • Reranking
  • PostgreSQL
  • Firestore
  • SQLAlchemy
  • DynamoDB
DevOps & Tools6 ENTRIES
  • Docker
  • GitHub Actions
  • Camunda BPM
  • Terraform
  • Git
  • Linux
AI-Assisted Development4 ENTRIES
  • Claude Code
  • GitHub Copilot
  • Custom MCP
  • Agent Tooling

$ sec.04 / about

About

Most AI demos don’t survive production. Mine do.

I own the full lifecycle - architecture, implementation, deployment, governance, and the 3am incident that proves it works. Open to senior engineering roles, freelance projects, and AI consulting.

The interesting problem in AI engineering is not getting a model to answer well once. It is what happens on the thousandth request, from the fourth brand, in the second language, when a product manager wants a new flow by Thursday. So I build for extensibility. New brands onboard through configuration rather than a deployment. Backend endpoints become agent tools automatically from their specs. Prompt, model, and flow control sit with the people who own the product, not the people who own the repo. The rest is discipline about constraints most demos ignore: latency budgets, token cost per node, output safety, and who is allowed to see what.

specialisations

Multi-Agent Orchestration
Planner, subagent, and parallel worker hierarchies on LangGraph and Google ADK - systems that decompose a request, act on it, and stay traceable while doing so
Conversational & Voice AI
Assistants across chat, WhatsApp, LINE, and speech - intent routing, tool use, multi-turn memory, and hot-word voice ordering at 10,000+ orders a month
RAG & Context Engineering
Hybrid retrieval, reranking, and citation-backed answers, with prompt caching and context budgeting that keep quality up and cost down
AI Observability & Governance
Distributed tracing for per-node latency and token cost, output-safety guardrails, RBAC and data governance - the layer that makes an agent system operable

$ sec.05 / recognition

Extraordinary Role Model
Top 1% of Nagarro employees · 4+ consecutive years for exceeding performance expectations and delivering high-impact AI solutionsNagarro Software
2022–2026
AWS R&D Event Presenter
Represented Nagarro's innovation in AI/ML and real-time commerce systems at the AWS R&D eventAmazon Web Services
2023

speaking & enablement

AI in the SDLC: sessions & workshops

I run internal sessions and workshops on AI-assisted development: agent configuration, prompt and context strategy, custom tooling, and folding Claude Code and Copilot into day-to-day engineering work.

  • Agent configuration
  • Prompt & context strategy
  • Custom MCP tooling
  • AI in the SDLC

education

Bachelor of Technology, Information Technology
Acropolis Institute of Technology and ResearchIndore, India
20182022

Certifications

Deep Learning Specialization
DeepLearning.AI
May 2026
VERIFY
LLMOps
DeepLearning.AI
Apr 2026
VERIFY
LangChain for LLM Application Development
DeepLearning.AI
Apr 2026
VERIFY
AI Agents in LangGraph
DeepLearning.AI
Jul 2024
VERIFY
Governing Agentic AI Systems
All Tech Is Human
Mar 2026
VERIFY
Responsible AI Foundations
All Tech Is Human
Mar 2026
VERIFY

$ sec.06 / get_in_touch

Get in Touch

Open to senior engineering roles, freelance projects, and AI consulting.

Response
Within 24h

Grab a virtual coffee

Prefer a casual chat? Let's discuss your project over a quick call.

Schedule Coffee Chat

$ sec.07 / faq

Tanmay Jain is an Associate Staff AI Engineer at Nagarro Software, promoted into the role in July 2026 after serving as Senior AI Engineer. He owns the architecture of a multi-tenant agent platform and leads engineering enablement on AI in the SDLC.
LangGraph, LangChain, and Google ADK for multi-agent orchestration; FastAPI for backend services; OpenCV and DLib for computer vision. On the model side: Claude API (Anthropic SDK), Gemini API, and OpenAI SDK, routed through LiteLLM for provider-agnostic fallback.
He architected a production three-tier hierarchy - a central planner, seven domain subagents, and parallel ReAct workers on LangGraph - serving web chat, WhatsApp, and voice for a multi-tenant commerce platform. Earlier he built single-agent, multi-tool architectures on Google ADK with intent-routed tool selection.
Book a call