AI & Automation Engineer (Python & LangChain)
AI & Automation Engineer (Python & LangChain)
Role Overview
Build production-grade GenAI systems, multi-agent autonomous workflows, RAG knowledge retrieval pipelines, and enterprise automation microservices.
WorkSaar is at the forefront of AI multi-agent software engineering. In this role, you will build autonomous AI agents that perform multi-step cognitive tasks, ingest proprietary enterprise knowledge via vector embeddings, and automate business processes across WhatsApp, web apps, and enterprise CRMs.
Indian Developer Hiring Process
⚡ Fast-Track 5-Stage SelectionOur hiring process is developer-first, transparent, and structured around practical software engineering aptitude—no rote algorithmic puzzles or trick questions.
AI Project & Code Review
⏱ 1-2 DaysAssessment of your Python repositories, prompt engineering examples, and RAG/Agent experiments.
AI Machine Coding Challenge
⏱ 48 HoursBuild an intelligent RAG or agentic workflow with FastAPI, vector search, and structured output parsing.
Technical Round 1 (Python & LLM Internals)
⏱ 60 MinsDeep dive into embedding spaces, retrieval precision, token budget optimization, and async pipelines.
Technical Round 2 (System Design for AI)
⏱ 45 MinsArchitecting resilient AI workflows with hallucination checks, rate limit management, and scalability.
HR & Offer Discussion
⏱ 24 HoursSalary confirmation (₹40,000 - ₹50,000 INR / month), joining schedule, and offer rollout.
Key Responsibilities
- Develop and deploy production AI agents using LangChain, LangGraph, or CrewAI and Python (FastAPI).
- Build advanced Retrieval-Augmented Generation (RAG) pipelines with semantic search and re-ranking.
- Integrate state-of-the-art LLM APIs (OpenAI, Anthropic, Google Gemini, open-source HuggingFace models).
- Manage vector embeddings and vector databases (Pinecone, ChromaDB, pgvector).
- Implement robust prompt engineering, output guardrails, token cost optimizations, and fallback strategies.
- Containerize AI services with Docker and deploy on scalable cloud infrastructure.
Technical Requirements (Core Skills)
- 1 to 3 years of software engineering experience in Python with a strong focus on AI/ML integration.
- Solid understanding of LLM architectures, context windows, token limits, and prompt templating.
- Experience building backend services with FastAPI or Flask and async Python.
- Hands-on experience with vector search, embeddings (text-embedding-3, bge-large), and RAG chunking techniques.
- Familiarity with Git, API authentication, Docker, and RESTful communication.
- Passionate about staying updated with rapid advancements in generative AI and autonomous agents.
Good to Have (Preferred)
- Experience fine-tuning open-source LLMs (Llama 3, Mistral) using LoRA / QLoRA.
- Experience with WhatsApp Cloud API automation (WhatCent platform integration).
- Demonstrated personal AI projects, HuggingFace spaces, or GitHub AI repos.
Developer Perks & Compensation Highlights
- Top-tier compensation: ₹40,000 - ₹50,000 INR / month (₹4.8 - ₹6.0 LPA).
- Generous cloud compute and LLM API budget for experimental research.
- 100% remote-first work culture with flexible hours.
- Comprehensive health and medical insurance.
- Work on bleeding-edge AI agent platforms with real enterprise customers.
Let’s Build Future Together.
