Rajendra Prasad Joshi

Rajendra Prasad Joshi

Agentic AI Engineer
India
Internship Remote

About Me

Agentic AI Engineer building, evaluating, securing, and deploying production-grade LLM agents, Enterprise Decision OS platforms, and Agentic RAG systems with Python, LangGraph, FastAPI, and FastMCP. Shipped to real users…

Experience

Agentic AI Intern

ALBACONNECT Inc. · Tokyo, Japan (Remote)
Apr 2026 - Present · 7 months

<p>Engineered an agentic AI bowling machine with an LLM planner as its decision-making brain; built a player knowledge base for Japan’s 15-player national squad from 2 years of ball-by-ball match data, using exploratory data analysis to derive batting strengths, weaknesses, dismissal patterns, and performance under pressure.</p><p> Built tool-augmented planning (database, knowledge base, hybrid retriever, reranker, Text-to-SQL): when a batsman is selected, the agent retrieves and reranks player-specific context, plans each delivery, observes the outcome, and adapts the next ball using thread-scoped short-term memory consolidated into persistent per-batsman long-term memory.</p><p> Ran offline evals with DeepEval: achieved 0.95 task completion, 1.00 step efficiency, 0.80 plan quality, 1.00 plan adherence, 0.87 argument correctness, and 1.00 tool correctness, while retrieval scored 0.99 contextual recall and 0.91 contextual precision.</p><p> Validated production readiness with P95 latency

PROJECTS

ALBA ONE (Enterprise Decision OS)

Duration : 01-Apr-2026 - 13-Nov-2026

<p> Architected a production multi-tenant Decision OS evolving a management Digital Twin prototype into a 6-stage LangGraph state</p><p>machine across 22 FastMCP servers (44 typed tools) and a bilingual (EN/JP) Next.js 15 cockpit; built hybrid retrieval</p><p>(PostgreSQL pgvector HNSW + BM25/PGroonga + RRF k = 60 + cross-encoder reranking) with SHA-256 chunk lineage.</p><p>• Engineered claim-level citation verification and an Expected Value of Sample Information (EVSI) decision judge; resolved</p><p>noisy-chunk low contextual relevance via semantic chunking to achieve 0.94 NDCG@10, 0.96 Recall@20, 0.91 MRR, 0.95 faithfulness,</p><p>100% citation verification, and 0.93 tool-call accuracy across 219 automated pytest/DeepEval gates.</p><p>• Enforced 7-layer defense-in-depth guardrails (deterministic regex/Unicode NFKC + semantic injection classifier, APPI/GDPR PII</p><p>redaction, PostgreSQL RLS tenant isolation, MCP HMAC capability tokens, groundedness validator, RBAC HITL gates, and Redis</p><p>token-budget breakers) alongside RS256/ES256 OIDC JWT auth (30s JWKS anti-amplification) and fail-closed startup checks.</p><p>• Shipped non-root (UID 10001) multi-stage Docker images, Helm/Argo Rollouts canary pipelines (auto-rollback at >1% 5xx or P95</p><p>>8s), and OpenTelemetry/Prometheus observability; built an 11-family automated red-team harness (0% ASR on 500+</p><p>adversarial prompts, Wilson 95% CI drift gates, and

Certifications

Bachelore degree

Vellore Institute of Technology, India · Vellore , Tamil Nadu , India · 2026

Skills

Python 3.12 asyncio OOP FastAPI Pydantic v2 SQLAlchemy 2.0 SQL REST APIs SSE APIs Git uv LangGraph LangChain Multi-Agent Orchestration Tool Calling Structured Outputs JEV-as-Judge Decision Scoring HITL Gates Thread-Scoped Memory Episodic Memory Semantic Memory KV-Cache Economics PEFT LoRA QLoRA Agentic RAG Self-RAG Corrective RAG GraphRAG Hybrid Search BM25 PGroonga Reciprocal Rank Fusion RRF Cross-Encoder Reranking Semantic Chunking Query Decomposition Claim-Level Citation Verification Model Context Protocol MCP FastMCP Multi-Server Tool Gateways HMAC Capability Tokens JSON-Schema Validation DeepEval RAGAS G-Eval LLM-as-a-Judge LangSmith 7-Layer Guardrails
Report this Profile?