Agentic AI Full-Stack AI Engineer (LangChain, RAG, Python)

Why This Role Matters

We’re a startup that is building Agentic AI tools that autonomously handle workflows across marketing, sales, and ops freeing people to think bigger, act faster, and create more. We believe agents should be collaborators, not chatbots. That’s why we’re hiring a full-stack developer who can help bring agentic intelligence into real-world business systems.

This is your chance to build something foundational in an emerging category agent infrastructure with real users, real feedback, and rapid iteration. You will thrive if you are a mission-driven builders, AI tinkerers, and startup engineers who want to make an impact and grow fast.

You won’t just be connecting APIs or calling GPT. You’ll help define the future of agent orchestration, contextual memory, multi-agent collaboration, and real-time task execution.

Requirement:

• Must have: 3 + yrs Python in production and 12 + months shipping LangChain/LlamaIndex or equivalent.
• Have shipped a LangChain or CrewAI project in production.
• Architect and deploy full-stack AI-powered agents that execute real-world tasks (e.g., send follow-ups, book meetings, update CRMs)
• Integrate LLMs (OpenAI, Claude, etc.) with structured logic, vector search, and third-party APIs
• Build memory-aware, context-persistent agent flows using LangChain, CrewAI, or your own orchestration logic
• Stand up RAG pipelines (Retrieval-Augmented Generation) with Pinecone, FAISS, or Chroma
• Deploy scalable, monitored services using Docker, CI/CD, and cloud (GCP/AWS)
• Collaborate with founders weekly to prioritize features, run fast experiments, and ship frequently

Tech Stack (You don’t need all, but you should have most)

Essential skills:

• Python (FastAPI / async) for core services
• LLM orchestration & tool use
• LangChain, AutoGen, CrewAI
• Function calling / tool selection APIs (OpenAI, Claude, etc.)
• Agent memory & RAG pipelines with Pinecone, Weaviate, Chroma, or FAISS
• Workflow & event routers
• n8n, Make.com, custom webhooks, or message queues (Redis, Pub/Sub)
• Any SaaS API via REST / GraphQL / OAuth2 (CRM, ERP, comms, payments, no hard limits)
• Docker + CI/CD (GitHub Actions / GitLab) on AWS, GCP, or Railway

Bonus Points if have:

• LangGraph or multi-agent planners
• Observability with Prometheus, Grafana, and structured logging
• React or Next.js for light internal UIs or dashboards
• Streamlit or Gradio for rapid prototyping

DevOps

• Cloud deployment: GCP, AWS, or Railway
• Basic observability: Prometheus, Grafana, or equivalents
• Versioning, rollback, and reproducibility best practices

You will excel if you

• Love building systems that do things, not just visualize them
• Are excited by LLM-powered software but realistic about its limitations
• Think like an engineer-product hybrid: user empathy + technical clarity
• Can translate vague business problems into actionable agent flows
• Prefer async, autonomous work cultures with high trust and high accountability
• Are a lifelong learner who experiments with AI tools on weekends for fun
• Write clean code and clean docs, README + Loom or Notion walkthroughs

Benefits

• Fully remote, async-friendly setup, work from anywhere with ~4h overlap in GMT+8
• Time for personal AI experiments or open-source contributions
• Learning budget (courses, books, or events you choose)
• Startup-level autonomy: shape the roadmap, ship to production in week 1
• Transparent feedback, weekly demos, no micromanagement
• Work on something foundational in the next wave of AI infrastructure
• Equity opportunity after 6 months for high-impact contributors

How to Apply

Please send us:

• Your CV or LinkedIn
• A GitHub repo, demo link, or short Loom/video walkthrough of an AI or automation project you’ve built
• In a few sentences, tell us about the most useful autonomous system you’ve created and what problem it solved

We’re not just looking for another engineer. We’re looking for a innovative creator in the future of intelligent software.

If you want to build agents that work while humans create, dream, and lead, apply now.

Job Type: Full-time

Pay: ₹500,000.00 - ₹700,000.00 per year

Benefits:

• Flexible schedule
• Work from home

Experience:

• Phyton: 3 years (Preferred)
• Production Rag: 1 year (Preferred)

Work Location: Remote