AI Engineer

Location: Remote (India)

Employment Type: Full-time / Contract

Experience: 3–7+ Years

We're looking for an AI Engineer to build production-ready AI agents that do far more than answer questions. You'll develop intelligent systems capable of reasoning, maintaining context, calling tools, integrating with business applications, and automating complex workflows.

This is a hands-on engineering role focused on building reliable, scalable AI products used in production—not just prompt engineering or chatbot development.

• Design and develop production-grade AI agents powered by modern LLMs.
• Build conversational systems with long-term memory and contextual understanding.
• Develop multi-step agent workflows capable of planning, reasoning, and executing actions.
• Integrate AI systems with APIs, CRMs, WhatsApp, Slack, calendars, databases, and other business tools.
• Implement tool/function calling architectures for seamless workflow automation.
• Design conversation memory, user memory, and state management systems.
• Build validation, guardrails, and safety mechanisms before executing actions.
• Create automated evaluation pipelines to measure AI quality, latency, accuracy, and cost.
• Optimize prompts, context windows, token usage, latency, and infrastructure costs.
• Develop scalable backend services supporting AI applications.
• Collaborate with product and engineering teams to build and launch AI-powered products.

• TypeScript / JavaScript
• Node.js
• Python

• REST APIs
• Webhooks
• Asynchronous processing
• Background workers / queues
• Authentication & Authorization
• Microservices and distributed systems

Hands-on experience with one or more of:

• OpenAI
• Anthropic
• Google Gemini
• Open-source LLMs (Llama, Mistral, etc.)

Strong understanding of:

• Function Calling / Tool Calling
• Retrieval-Augmented Generation (RAG)
• Prompt Engineering
• Structured Outputs
• JSON Mode
• LLM Evaluation

Experience building AI agents with:

• Multi-step reasoning
• Tool orchestration
• State machines
• Conversation memory
• User memory
• Workflow automation
• Human-in-the-loop approvals
• Multi-agent systems (preferred)

Experience with one or more frameworks:

• LangGraph
• OpenAI Agents SDK
• CrewAI
• AutoGen
• Mastra
• Vercel AI SDK
• LangChain
• LlamaIndex

Experience with:

• PostgreSQL
• Supabase
• Redis
• Vector Databases (Pinecone, Weaviate, Chroma, pgvector, etc.)

• Docker
• Kubernetes

Browse our curated collection of remote jobs across all categories and industries, featuring positions from top companies worldwide.

• AWS / GCP / Azure
• CI/CD Pipelines
• MCP (Model Context Protocol)
• AI Observability (Langfuse, OpenTelemetry, etc.)
• Voice AI or Computer Vision experience

We're looking for engineers who:

• Think like systems engineers.
• Build reliable and scalable production software.
• Care about performance, security, maintainability, and cost optimization.
• Enjoy solving complex AI and backend engineering challenges.
• Have experience shipping AI products into production.

Experience building AI solutions for:

• Customer Support
• Sales Automation
• Recruitment
• Healthcare
• FinTech
• Internal Enterprise Tools
• Workflow Automation

• 3–7+ years of software engineering experience.
• 1–3+ years of hands-on experience building production LLM applications.
• Strong backend engineering fundamentals.
• Experience integrating AI into real-world business workflows.
• Excellent communication and problem-solving skills.

• Opportunity to build cutting-edge AI products.
• Work with global startups and enterprise clients.
• Fully remote work environment.
• Flexible working hours.
• High ownership and autonomy.
• Competitive compensation based on experience.
• Exposure to the latest AI technologies and production-scale systems.