Senior AI Engineer – GenAI Systems & AI Agent Architecture

Job Title : Senior AI Engineer – GenAI Systems & AI Agent Architecture

Location : Noida / Hybrid

Type : Full-time

Compensation : Competitive – based on experience (CTC + ESOP options)

About YoLearn.ai

YoLearn.ai is building the world’s most emotionally intelligent, personalized learning OS — powered by AI tutors, coaches, and study buddies. Our platform blends deep pedagogical thinking with cutting-edge GenAI, LLMs, and agentic architectures to transform how students learn and how teachers teach.

We're looking for a Senior AI Engineer with a strong foundation in machine learning , LLMs , and AI agent infrastructure — who has built real AI apps , not just played with notebooks. You’ll work closely with the founder, AI research engineers, backend devs, and product teams to power everything from tutoring agents to live multimodal avatars.

Responsibilities AI & ML System Development

Architect, train, fine-tune, and deploy models (ML + DL + LLMs)

Build and scale GenAI applications : RAG systems, recommender engines, forecasting models

Engineer robust AI agents with memory, personalization, tool access, and reasoning logic

Handle multi-agent orchestration , streaming audio / video interfaces , and real-time AI flows

Engineering & Infra

Design and optimize data pipelines : cleaning, preprocessing, feature engineering

Build production APIs (FastAPI preferred) for AI tools and core platform functionality (billing, notifications, usage logs, profiles, history)

Manage CI / CD pipelines , containers (Docker), orchestration (Kubernetes), and deployment workflows

Integrate with AWS services : Sagemaker, Bedrock, Lambda, EC2, ECS / EKS, Redis, S3, Athena, Step Functions , etc.

Work on LLM fine-tuning , retrieval augmentation, and model context protocols (MCP)

GenAI & LangChain Ecosystem

Build GenAI tools using OpenAI, LLaMA, DeepSeek, Mistral , etc.

Use LangChain , LLM orchestration frameworks , and vector DBs (Qdrant, FAISS, Weaviate, pgvector)

Construct RAG-based assistants , multi-turn memory, agent-based logic

AI Product Features

NLP tasks (NER, summarization, embeddings, retrieval, QA)

Image / video model integration (optionally GANs, captioning, OCR)

Build smart learning systems : time series forecasting, recommendations, knowledge graphs

Integrate token tracking, user usage monitoring, analytics

‍ Required Skills✅ Core

3–6+ years hands-on experience in AI / ML / LLM development and deployment

Python (advanced), OOPs, NumPy, Pandas, SQL (MySQL / PostgreSQL)

Data preprocessing, EDA, model training / tuning / evaluation

ML algorithms (regression, classification, clustering)

DL (ANN, CNN, RNN, LSTM, Transformer), GANs

NLP (NER, summarization, sentiment, tokenization, embeddings)

✅ Dev & Ops

FastAPI / Flask / Node.js (for backend API)

Git, GitHub / Bitbucket, CI / CD pipelines

Docker, Kubernetes, AWS (EC2, Lambda, S3, Sagemaker, etc.)

Redis, Supabase, Firebase, PostgreSQL

Git-based testing, debugging, and logging practices

✅ GenAI & LLM Stack

LangChain, LlamaIndex, OpenAI APIs, Bedrock models

Vector DBs (Qdrant, FAISS, pgvector)

RAG architecture, memory layers, streaming AI

Audio / Video AI tool integration (e.g., Whisper, AssemblyAI, Deepgram, WebRTC)

Model fine-tuning, inference optimization (PEFT, LoRA, quantization)

Bonus (Nice to Have)

Built, finetuned, trained or deployed LLM agents with real-world users or scale

Experience in K-12 EdTech, AI tutors, or learning platforms

Exposure to Lex, Connect, Step Functions, CloudWatch, IAM roles

Familiarity with agent frameworks like LangGraph, AutoGen, CrewAI

Basic frontend understanding (React, Next.js) to collaborate with full-stack teams

Experience with Agentic memory layer, prompt engineering , Agentic tools, RAG systems, MCP servers, Google's A2A protocol , vertex AI .

Qualifications

B.E. / B.Tech / M.Tech in Computer Science, AI, Data Science, or related fields

Strong coding and algorithmic reasoning skills

Strong written communication and technical documentation ability

Work Culture & Reporting

Team : Report to CTO and Founder, collaborate with AI agents, backend, and UI / UX teams

Culture : High ownership, agile delivery, startup intensity + deep tech creativity

Tools we use : GitHub, Linear, Slack, GCP, Supabase, Notion, Vercel, LangChain, AWS

How to Apply

Send your resume, GitHub, portfolio (if any), and links to AI / LLM projects you’ve built (not just notebooks) to :

contact@yolearn.ai

www.yolearn.ai