I'm Vishnu A C — a Software Engineer with 1.7 years of experience crafting scalable microservices, cloud-native architectures, and AI-powered solutions.
With 1.7 years at Anunta Technology, I architect production-grade backend systems at real-world scale. I've slashed API latencies by 42%, boosted database efficiency by 90%, and compressed release cycles from 2 days to under 2 hours.
I specialize in building high-throughput microservices in Go and Python, designing agentic AI workflows with AutoGen and RAG pipelines, and orchestrating cloud-native deployments on Azure. Passionate about turning complex distributed systems into clean, maintainable architectures that scale.
From building a zero-downtime API gateway with distributed rate limiting, to crafting RAG-powered legal chatbots and agentic AI platforms — I thrive at the intersection of backend engineering and artificial intelligence. Every system I build is designed to be fast, resilient, and production-ready.
Built production-grade agentic AI assistants using graph-based AutoGen workflows and RAG with ChromaDB. Designed multi-agent collaboration pipelines for enterprise automation.
Led optimization of a hybrid cloud monitoring platform for 1000+ VMs, reducing API latency by 50%, achieving 99% uptime, cutting cloud configuration time from hours to minutes, lowering Azure monitoring costs by 40%, and reducing QA bugs by 80%.
Developed a high-throughput async monitoring service, enabling 10x higher concurrency, improving DB performance by 40%, reducing runtime errors by 60%, and with only a 5% QA bug rate.
Modernized deployment pipelines using Go and RabbitMQ. Compressed release cycles from 2 days → under 2 hours.
Took ownership and migrated cost analytics from Python to Go. Reduced analytics runtime from 5 min → under 100ms — a 1800× improvement.
Personal AI Assistant
Containerized local LLM assistant built with Go and Ollama. Features streaming responses, conversation memory, and complete data privacy — all running locally.
func StreamResponse(prompt string) {
client := ollama.NewClient()
stream := client.Chat(prompt)
for chunk := range stream {
fmt.Print(chunk.Content)
}
}ATS & Interview Engine
AI-powered resume scoring using sentence embeddings. Automates candidate screening with configurable scoring weights and semantic skill extraction.
model = SentenceTransformer("all-MiniLM")
resume_vec = model.encode(resume)
job_vec = model.encode(job_desc)
score = cosine_sim(resume_vec, job_vec)Legal RAG Chatbot
RAG-powered chatbot for Indian legal documents. Uses ChromaDB vector retrieval for accurate, context-aware legal assistance from a corpus of legislation.
collection = chroma.get_collection(
name="indian_law"
)
results = collection.query(
query_texts=[user_query],
n_results=5
)API Gateway
Lightweight, high-performance API gateway in Go. Features dynamic zero-downtime routing via PostgreSQL + Redis pub/sub, distributed rate limiting with sliding window algorithms, centralized auth, and async telemetry through Kafka.
func RateLimit(key string) bool {
now := time.Now().UnixMilli()
pipe := redis.Pipeline()
pipe.ZRemRangeByScore(key,
"0", fmt.Sprint(now-window))
pipe.ZAdd(key, now, now)
return pipe.ZCard(key) <= limit
}Confluence AI Companion
AI-powered Confluence assistant that features Page Assistant, Smart Gap Filler, Confidentiality Scanner, Focus Mode Summarizer, Quiz Generator, and Timeline Generator for intelligent content interaction.
confluence = Confluence(
url="https://team.atlassian.net"
)
pages = confluence.get_all_pages()
embeddings = ollama.embed(pages)
response = ollama.chat(
model="llama3", context=docs
)ML Activity Monitor
ML-powered work activity monitor using Random Forest classifier. Detects and classifies user activity states in real-time for productivity insights.
model = RandomForestClassifier(
n_estimators=100,
max_depth=10
)
model.fit(X_train, y_train)
state = model.predict(live_data)I'm currently looking for new opportunities. Whether you have a question, a project idea, or just want to say hello — my inbox is always open.