AI Engineer

Cosmofeed; Gurugram District; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Cosmofeed in India is seeking two AI Engineers to build and scale AI-powered products for thousands of creators. You will own AI systems end-to-end—from ideation and model selection to deployment, monitoring, and continuous production improvements.

The role requires 3+ years of software engineering experience, strong Python, and hands-on work with LLMs, RAG pipelines, vector databases, and cloud deployment in a fast-growing startup.

Qualifications

• Minimum 3 years of professional software engineering experience.
• Strong proficiency in Python and experience with modern AI frameworks.
• Hands-on experience building LLM-powered applications using OpenAI, Claude, Gemini, or open-source models.
• Experience designing and deploying Retrieval-Augmented Generation (RAG) systems using vector databases and embeddings.
• Strong understanding of prompt engineering, tool orchestration, structured outputs, and AI evaluation techniques.

Responsibilities

• Build, deploy, and own AI-powered products from concept to production.
• Design and implement LLM-powered workflows, AI agents, copilots, and intelligent automations.
• Develop reliable RAG pipelines using vector databases and enterprise data sources.
• Build production-ready text and voice AI agents with tool calling, memory, orchestration, and evaluation.
• Fine-tune prompts, optimize inference performance, and continuously improve AI systems based on user feedback.
• Collaborate with product, design, and engineering teams to integrate AI capabilities into customer-facing products.
• Monitor AI systems in production, ensuring reliability, safety, latency, and cost efficiency.
• Stay up to date with the latest advancements in generative AI and rapidly prototype new capabilities.

Skills

Python

LLM development

Prompt engineering

Cloud deployment

API design

Tools

OpenAI

Claude

Gemini

Pinecone

Weaviate

Chroma

GitHub Copilot

Job description

About the role

SuperProfile helps thousands of creators run their businesses — payments, memberships, courses, and bookings — on a platform handling 500M+ requests a day. We're a small, senior engineering team, and we're hiring two AI Engineers to build and scale AI-powered products that directly impact creators. You'll own AI systems end-to-end — from ideation and model selection to deployment, monitoring, and continuous improvement in production.

What you'll do

• Build, deploy, and own AI-powered products from concept to production.
• Design and implement LLM-powered workflows, AI agents, copilots, and intelligent automations.
• Develop reliable Retrieval-Augmented Generation (RAG) pipelines using vector databases and enterprise data sources.
• Build production-ready text and voice AI agents with tool calling, memory, orchestration, and evaluation.
• Fine-tune prompts, optimize inference performance, and continuously improve AI systems based on user feedback.
• Collaborate closely with product, design, and engineering teams to integrate AI capabilities into customer-facing products.
• Monitor AI systems in production, ensuring reliability, safety, latency, and cost efficiency.
• Stay up to date with the latest advancements in generative AI and rapidly prototype new capabilities.

Languages: Python, TypeScript, Go, Node.js

AI Infrastructure: Vector Databases (Pinecone, Weaviate, Chroma), RAG, Embeddings, Prompt Engineering, Function Calling, MCP, Evaluation Frameworks

Frontend: React, Next.js

Databases & Storage: MongoDB, Redis, DragonflyDB, S3 / R2

Search & Analytics: OpenSearch, Druid / Imply, Mixpanel

Messaging & Jobs: Kafka, SQS, BullMQ

Cloud & Infra: GCP, GKE / Kubernetes, AWS, Cloudflare, Vercel, Docker

Integrations: Meta / Instagram, WhatsApp, Telegram, Discord, Shopify, Google Workspace, Zoom, YouTube, Slack, Zoho, Vimeo

What we're looking for

• Minimum 3 years of professional software engineering experience, with significant experience building and deploying AI-powered applications in production.
• Strong proficiency in Python, along with experience using modern AI frameworks and tooling.
• Hands-on experience building LLM-powered applications using OpenAI, Claude, Gemini, or open-source models.
• Experience designing and deploying Retrieval-Augmented Generation (RAG) systems using vector databases and embeddings.
• Strong understanding of prompt engineering, tool orchestration, structured outputs, and AI evaluation techniques.
• Experience building AI agents (text and/or voice) beyond simple API integrations.
• Strong familiarity with Claude Code, Cursor, GitHub Copilot, or similar AI-assisted development tools.
• Experience deploying AI applications on cloud platforms with monitoring, logging, observability, and cost optimization.
• Strong software engineering fundamentals including system design, APIs, databases, scalability, and security.
• Ability to work independently, own projects end-to-end, and collaborate effectively in a fast-moving startup environment.

Why this role

• Build AI products used by thousands of creators every day.
• Work on cutting-edge generative AI, autonomous agents, and production-scale LLM systems.
• Own projects end-to-end with real product impact from day one.
• Join a lean, high-performing engineering team with minimal bureaucracy and high autonomy.
• Solve challenging engineering problems at scale while working with the latest AI technologies.