Key Responsibilities:
Act as technical architect for SmartLearn’s MVP, setting system architecture, data flow design, and
scaling benchmarks.
Ensure seamless integration across AI, backend, and frontend components.
Define latency, reliability, and security standards.
Provide technical leadership to backend/frontend engineers.
Oversee global-scale deployment architecture, including multi-region latency optimization, CI/CD
pipelines, and security standards.
Architect robust multi-agent workflows using LangGraph, LangChain, or CrewAI.
Leverage prompt optimization frameworks (DSPy, Optix, Arize Phoenix) for reliable LLM pipelines.
Implement real-time retrieval pipelines with Playwright, Firecrawl, Puppeteer.
Build dual-path lesson generation (creative drafting + grounded synthesis from web/YouTube).
Integrate coding sandboxes (Colab, JupyterLite) with automated grading.
Develop OCR and browser automation agents with Tesseract, PaddleOCR, Playwright, Puppeteer.
Enable image and diagram generation with diffusion and multimodal LLMs.
Deploy context-aware AI tutor with chat and voice (STT/TTS, OCR-enabled).
Design and maintain scalable Python/FastAPI APIs with semantic search and caching.
Manage LLM Ops: prompt engineering, optimization, evaluation, and deployment pipelines.
Utilize AI coding assistants (Claude Code, Codex, Cursor) for productivity and rapid prototyping.
Architect long-term memory and knowledge graph structures for adaptive personalization.
Required Skills:
Bachelor’s or Master’s in Computer Science, Machine Learning, AI, or related field
6+ years of production software engineering experience
Proven ability as a technical architect for scalable, secure AI applications
* AI coding copilots (Claude Code, Codex, Cursor)
Multi-agent frameworks (LangGraph, LangChain, CrewAI)
LLM integration and workflow ops (Claude, GPT, Gemini, Bedrock)
On-the-fly RAG and web scraping (Playwright, Firecrawl, Puppeteer)
Sandbox integration (Colab, JupyterLite), auto-grading (unit tests, LLM rubrics)
OCR and computer vision (Tesseract, PaddleOCR, EasyOCR)
Browser automation (Playwright, Puppeteer, Selenium)
Image generation (diffusion models, multimodal LLMs)
Python + FastAPI backend expertise
Realtime optimization (async, caching, streaming APIs)
Vector DBs (Pinecone/FAISS), Redis, Postgres
Cloud infrastructure (AWS/GCP: Lambda, S3, RDS, autoscaling, monitoring)
Exposure to frontend teamwork (React, Next.js, Tailwind)
Memory-augmented RAG and knowledge graphs (Neo4j, RDF, GraphDB)
Prompt optimization (DSPy, Optix, metric-driven evaluation)
Need to have AI native exposure in the past projects
Preferred (Bonus) Skills:
Bayesian/hybrid prompt optimization methods
Few-shot and meta-prompting techniques
Strong async communication and collaboration in remote environments
Startup experience with high ownership and adaptability
Job Type: Contractual / Temporary
Contract length: 3-6 months
Pay: ₹80,000.00 - ₹90,000.00 per month
Benefits:
Work from home
Application Question(s):
Can you join immediately ?
Do you have your own Laptop with stable network ?
Are you comfortable with work from home
Work Location: Remote