Open to opportunities

AkashNikam

Building AI-powered workflows that make engineering teams 50-70% faster. AI engineer at John Deere, specializing in multi-agent systems, RAG, and production AI backends.

5+
Years experience
12
Agents built at Deere
50%โ†‘
Team velocity gains
6+
Projects shipped
agent-orchestrator.py
๐Ÿค–
12 Agents
deployed at Deere
โšก
50-70%
velocity gain
๐Ÿ”—
Full SDLC
AI coverage
๐ŸŒ
3-4 Teams
actively using
Akash Nikam

About me

I'm an AI engineer who builds agentic systems for a living. Currently a Senior Software Engineer at John Deere, where I design and ship multi-agent platforms that change how engineering teams actually work - the intersection of LLMs, backend systems, and shipping real things people use.

The thing that drives me: I learn by building. When I want to understand something - OAuth and webhooks, RAG retrieval, bounded AI pipelines - I don't just read about it, I ship a working version. That's where ZapBridge, ARKEN, and PlantIQ came from: each one started as a question I couldn't answer from a blog post.

I'm allergic to hand-waving. I'd rather say "I haven't built that yet" and go build it than fake my way through - and when I build, I care about the why behind every decision: timing-safe validation, idempotency, graceful degradation, not just code that happens to run.

Before Deere I spent 2+ years at Mavenir building Go microservices for telecom-grade analytics on Kubernetes. Outside of code: dissecting new architectures and occasionally writing on Medium about things I figured out the hard way.

Pune, IndiaOpen to remoteAI EngineerAgentic Systems

What I work with

Technologies I reach for when shipping real systems, not just listed but actually used.

AI & Agents
Agentic AILLMsClaude / MCPRAGLangGraphVector Search / QdrantEvalsPrompt Engineering
Backend
GoPython / FastAPIgRPCProtocol BuffersREST APIsMicroservices
Frontend
TypeScriptReact + ViteJavaScriptWebRTCSSE / Streaming
Databases
PostgresMongoDBRedisDynamoDBCouchDBSinglestore
DevOps & Infra
DockerKubernetesNginxCI/CDGitHub Actions

Where I've worked

5+ years building AI agent systems and the production backends behind them.

Full profile โ†—
John Deere
Senior Software Engineer - AI Agents & Backend
Oct 2023 - Present ยท Pune, Hybrid
AI Agent Platform
  • Architected a 12-agent AI platform automating the full engineering SDLC, from epic creation and user-story writing to bug triage, code review, and infra docs, with specialized agents (planner, developer, reviewer, static-analyzer, link-tester) coordinated through a durable LangGraph orchestration layer. Deployed across 3-4 engineering teams, cutting engineering time by 50-70%.
  • Built a code knowledge graph that parses an entire codebase into a call/dependency graph, ranks the most important nodes with PageRank, and renders an interactive dependency visualization, giving every agent a structural map of the code.
  • Engineered a graph-based RAG retrieval pipeline that grounds agents in real code by blending keyword search, PageRank importance, and graph-neighbor proximity with task-type weighting, so each agent sees only the relevant code and hallucination stays suppressed.
  • Designed durable, local-first execution with a custom LangGraph checkpointer over local SQLite, so agent runs are resumable and crash-safe with no central server, keeping all source and state on the developer's machine.
  • Wired agents into automated quality gates (lint, type-check, test, smoke-test, and duplicate-detection) run by dedicated reviewer, static-analyzer, and link-tester agents as merge blockers on every change.
  • Rolled out the agent platform across 3-4 engineering teams through hands-on KT sessions, integrating directly into existing workflows. Teams shifted from writing to reviewing and validating AI-generated output, backed by a structured quality-gate process to approve results before adoption.
  • Built a real-time machine visualization UI from scratch using GitHub Copilot with no prior reference on the platform, delivered ~50% faster than the traditional estimate.
Production RAG Platform
  • Built a production RAG copilot for manufacturing SOPs, now in pilot with technicians querying in production.
  • Engineered 3-lane parallel retrieval: Qdrant hybrid (BM25 + dense vectors) and an entity graph, fused via RRF, with correction and outcome boosting synced into the vector payload.
  • Enforced secure multi-tenant isolation: plant_id scoping on every query, RBAC, prompt-injection defence, and append-only audit logs, validated against a real container.
  • Built a 50-question eval harness with cross-model grading (Claude Opus + GPT-4o), wired into CI as a ratchet that fails the build on any quality regression.
  • Designed a 6-layer fallback architecture with zero silent failures, degrading gracefully across retrieval and model layers under partial failure.
Mavenir
Member of Technical Staff I (R&D)
Mar 2022 - Oct 2023 ยท 1 yr 8 mos ยท Remote
  • Built a production Go service for a high-frequency analytics notification system - polls CouchDB every 100ms, matches epoch-time triggers, dispatches notifications, and auto-expires entries after 30 minutes. Used goroutines and channels for concurrent, non-blocking delivery at scale.
  • Used SingleStore for distributed data storage and document management across Go microservices in production - hands-on with its query model, distributed data patterns, and performance characteristics in a real-time service architecture. Also worked with CouchDB for document management.
  • Designed and implemented versioned OpenAPI specifications in Go for a microservice platform, making APIs fully configurable for future version changes and significantly reducing migration effort.
  • Contributed to NWDAF application development on a microservice architecture in Go - service-to-service APIs, distributed state management, and production deployment across Kubernetes-based infrastructure.
  • Worked with Go, Docker, and Kubernetes throughout R&D - containerized services, K8s deployment patterns, and service-mesh communication in a production microservice environment.
  • Collaborated cross-functionally with R&D teams to design, build, and ship Go services handling concurrent workloads, real-time data pipelines, and distributed notification systems at telecom scale.
Mavenir
Graduate Engineer
Mar 2021 - Feb 2022 ยท 1 yr ยท Remote
  • Worked hands-on with Go, Docker, and Kubernetes in a production microservice architecture - containerized service deployment, K8s service-mesh patterns, and inter-service communication across distributed components.
  • Wrote unit tests across 2-3 microservices, improving coverage and reliability of core services - disciplined about testing and regression prevention from day one.
  • Resolved bugs on the Prediction Application by triaging issues, identifying root causes, and shipping fixes under production constraints - building strong debugging instincts across distributed Go services.
  • Used CouchDB for document management alongside Go microservices in a distributed data architecture.

Things I've built

Personal and open-source work - agentic AI, RAG, and event-driven systems.

Awards & Recognition

Recognized by John Deere for impactful, cross-functional contributions.

WOW Award April 2026
๐ŸŒŸ WOW! Award
Exceptional cross-functional impact by driving TDP, supporting PDP and Display CoC project
JDI R&R Program ยท Apr 2026
Star of the Month Award
โญ Star of the Month
Technical strength with customer focus and innovative approach for PDP and TDP project
JDI R&R Program ยท Nov 2025
WOW Award April 2025
๐ŸŒŸ WOW! Award
Business Logic Development for Rebale Documentation
JDI R&R Program ยท Apr 2025

Thoughts & articles

I write about AI systems, distributed infrastructure, and lessons from shipping production software.

Read on Medium โ†—

Got something interesting?

Whether it's a collaboration, a project idea, or just a curious question, I'm all ears.

akashvnikam@gmail.com