Bengaluru, India

AI systems,
built to be measured.

I am Aprameya, an AI engineer at Oracle. I take agentic and generative AI from a customer's first conversation to production: retrieval, agent design, GPU serving, and the infrastructure underneath.

Cloud Engineering · AI Oracle Five measured projects

Experience

2025 – present
Jun 2026 – Present

Oracle

Cloud Engineering · AI (L2)
  • Technical scoping lead and point of contact on EMEA engagements across GPU serving, guardrails, voice AI, MCP and agentic automation.
  • Built a three-agent ServiceNow suite for a public-sector client: natural-language search over 1M+ tickets in under 7 seconds, hybrid search over 500K+ multilingual articles, ticket creation under a minute.
  • Built a multilingual legal and tax RAG assistant for a national tax authority, so citizens can ask questions in their own language.
  • Delivered OCI infrastructure end to end: landing zones, networking, storage, IAM, VM migration and disaster recovery, automated with Terraform.
Jul 2025 – May 2026

Oracle

Cloud Solution Engineer (L1)
  • Built a trademark platform for a government ministry, exposed as two APIs: similarity over 500K+ images with multilingual text and compliance rules on a CPU-only machine, and open-source image generation and editing on NVIDIA CUDA GPUs through a custom ComfyUI module.
  • Primary developer of internal AI tools used across teams, from a document generator to a security-review agent.
Jan 2025 – Jul 2025

Oracle

Project Intern
  • Built the Solution Document Generator on LangGraph and OKE, and a security-review agent for go-live projects.

About

01

I work on applied AI: agentic systems, retrieval, and the serving layer under them. Most of what I ship is measured, and each project above carries its own benchmark. When something does not hold, it is reported next to the result that does.

Before Oracle I studied electronics at JSS Science and Technology University, where I published on SLAM and VSLAM and hold a design patent. I still keep the research habit: state the question, fix the variables, report the interval.

LinkedIn · GitHub · Hugging Face

Agents & RAG

ADK, LangGraph, LangChain, Deep Agents, OpenAI SDK, MCP; hybrid retrieval, pgvector, guardrails, agent memory

Inference & training

vLLM, llama.cpp, speculative decoding, FP8 KV cache, CUDA, LoRA fine-tuning, Hugging Face

Cloud & infrastructure

AWS, Google Cloud, OCI (Enterprise AI, Dedicated AI Clusters, OKE, landing zones, VCN, IAM, DR), Terraform

Languages & DevOps

Python, TypeScript, SQL; Linux, Docker, Kubernetes, Helm, Prometheus, CI/CD

Contact

Building something that needs to work?

I am open to applied AI and forward-deployed engineering roles. The fastest way to reach me is email.