Job Description
What You’ll Work On
Build and scale AI-first recruiting automation workflows for candidate sourcing, matching, and communication.
Develop robust web scrapers with anti-ban techniques (proxies, headers, sessions, rate limits).
Design and automate workflows using n8n, Clay, CrewAI, or custom Python pipelines.
Build backend services and APIs using Python (FastAPI/Flask) to integrate internal systems and AI models.
Design, optimize, or maintain RAG pipelines (vector DBs like FAISS, Chroma, Pinecone).
Experiment with LLMs (GPT, Claude, Llama) and create tool-using agentic systems.
Implement or learn MCP (Model Context Protocol) to build multi-system AI workflows.
Deploy prototypes and microservices on AWS (Lambda, EC2, S3, API Gateway).
Rapidly prototype POCs using Streamlit, FastAPI, or light full-stack approaches.
Research AI tools, scraping tools, agent frameworks, and evaluate best-fit solutions.
Collaborate asynchronously with a remote team and US-based leadership.
Ideal Candidate Profile
We are looking for someone who demonstrates builder energy—curious, fast-learning, and able to execute.
Required Skills
Solid programming skills in Python (preferred) or JavaScript.
Experience with web scraping techniques: proxies, rotating user agents, cookies, headless browsers.
Practical experience or strong interest in automation platforms (n8n, Clay, CrewAI) and custom workflow scripting.
Basic backend experience with FastAPI/Flask/Node.
Understanding of LLMs (GPT, Claude, Llama) and ability to build small apps or integrations using them.
Familiarity with retrieval systems, vector stores, or embedding-based search.
Comfort with designing or understanding AI agents (multi-step reasoning + tool use).
AWS basics: EC2, S3, Lambda, permissions, deployments.
Strong research ability and willingness to learn unfamiliar tools quickly.
Ability to work independently, deliver fast prototypes, and iterate with feedback.
Bonus Skills (Nice-to-Have)
Experience with LangChain, LlamaIndex, Hugging Face.
Exposure to MCP ecosystem.
Knowledge of Docker, CI/CD, or light DevOps.
Experience in recruiting/talent acquisition automation.
Full-stack prototyping experience (Streamlit, simple React, or Gradio).
What We Offer
Paid internship with direct mentorship from AI engineers and founders.
Fully remote, flexible work environment.
Opportunity to work on real AI automation systems used in US healthcare staffing.
Experience in high-value areas like scraping, agents, RAG, and workflow automation.
Strong potential for full-time employment based on performance, ownership, and results.
Selection Process
Pre-screening questions + small assessment
Technical interview (Python + scraping + AI fundamentals)
Final decision based on execution speed, problem-solving, and communication
Job Types: Full-time, Permanent, Fresher, Internship
Contract length: 3 months
Pay: ₹10,000.00 – ₹20,000.00 per month
Application Question(s):
• Share a link or GitHub repo of a project where you built a web scraper or automation workflow. What data were you extracting and what challenges did you solve?
• Describe how you prevent your scrapers from getting blocked. What techniques or tools do you use (e.g., proxies, headers, sessions, delays, browser automation)?
• Have you built anything using LLMs (GPT, Claude, Llama) or AI agents? If yes, describe it briefly. If not, what would you build first?
• Rate yourself (0–10) in Python or any other scripting language and explain one automation or script you built recently and what problem it solved
Work Location: Remote