AI/ML Engineer
Currently at Datavalley Inc · Based in London · Open to AI/LLM Engineering Roles
I build the systems behind the AI - RAG pipelines, multi-agent coordination, and MLOps infrastructure. Not demos. Production.
UK Graduate Route Visa - Full-time work authorised, no sponsorship required
15+
Automation Pipelines
30+
Integrated Services
100+
Engineers Mentored
Production
Datavalley CRM
What I Build
Production-grade AI systems with measurable outcomes, structured orchestration, and deployment readiness
Agentic Systems
Designing structured multi-agent workflows with clear execution boundaries and controlled orchestration.
Retrieval-Augmented Generation (RAG)
Modular RAG pipelines with explicit separation of retrieval, orchestration, prompting, and evaluation.
Production ML Pipelines
Scalable ML systems with observability, reliability, and deployment readiness.
Featured Projects
View AllRAG Foundry
Framework for building RAG systems with separated retrieval, ranking, and generation components, plus tools to measure quality across datasets.
Core Idea
Separate retrieval, orchestration, prompting, and evaluation into independent, testable modules
Architecture
Plugin-based retriever system with swappable vector stores and configurable chunking strategies
What You Can Reuse
Evaluation harness with dataset-driven metrics (GitHub template available)
Agiorcx Lib
Library that provides an execution layer for AI agents, with explicit control flow, error handling, and guardrails for production use.
Core Idea
Explicit control flow for agents with guardrails, rollback mechanisms, and execution logging
Architecture
State machine-based orchestration with pre/post execution hooks and audit trails
What You Can Reuse
Agent coordinator pattern with guardrails (library + examples)
Orion - Production Deep Research Agent
Stateful multi-source research agent solving five failure modes: hallucination propagation, context rot, stateless amnesia, opaque failures, and read-only outputs.
Core Idea
Planner agent decomposes queries into sub-tasks with explicit source routing, sub-agents execute in parallel across PDF, URL, and Google Drive sources
Architecture
Typed AgentResult<T> returns with source attribution - unsourced claims flagged and never published
What You Can Reuse
Multi-source research orchestration pattern with attribution tracking (reference implementation)
Evallit
Evaluation toolkit for LLM and RAG systems that runs dataset-based checks, records metrics, and exposes hooks for monitoring and debugging.
Core Idea
Define test datasets upfront, run automated evaluation passes, track metric trends over iterations
Architecture
Pluggable metric system (ROUGE, semantic similarity, custom scorers) with experiment tracking
What You Can Reuse
Evaluation pipeline template with metric collectors and reporting dashboards
Where I've Built
AI/ML Engineer
Datavalley Inc
Sep 2025 - Present
- →Lead scoring model in production, integrated via FastAPI into live CRM UI
- →15+ automation pipelines orchestrating 30+ services (N8N + Airflow)
- →Agentic LangChain workflows replacing manual decision steps
MSc Data Science (AI/ML)
University of Roehampton
Jan 2024 - Sep 2025
BTech IT
JNTUK
Aug 2019 - Jun 2023
Sai Harsha Logs
View AllNotes & Lessons from AI engineering and system building
Why AI Systems Fail in Production
From Ch.1 - Fundamentals of AI Systems | Production AI Systems Engineering...
Your LLM Doesn't Feel. Regulators Still Classify Its Behavior as Risk
By Sai Harsha Kondaveeti at Garvaman AI...
Currently open to AI/LLM Engineering roles in London
Hybrid or remote. UK Graduate Route Visa. Full-time work authorised. No sponsorship required.
Fastest way to reach me: