Remotely
prompt engineeringlanggraphragembeddingsvector databasesautogencrewaimulti agent
Job Description
📋 Description
- Architect, develop, and productionize Agentic AI and Generative AI solutions
- Design multi-step reasoning agents, tool-calling workflows, memory systems, planning
- Build scalable RAG pipelines with embeddings and vector search
- Evaluate foundation models for accuracy, latency, cost, scalability
- Lead prompt engineering, model routing, fine-tuning, optimization
- Own high-impact AI architecture decisions for scalable, secure apps
🎯 Requirements
- 10+ years software engineering, 4+ years with AI/ML systems
- 2+ years building LLM/agentic AI in production
- Deep expertise in LLM app development, RAG, embeddings, vector DBs
- Experience with multi-agent systems, tool calls, memory management
- Strong Python and scalable distributed systems
- APIs, microservices, cloud-native architectures
🎁 Benefits
- Fully remote from India
- Competitive compensation ₹30,00,000–₹50,00,000
- Full-time employment
- High-impact leadership with ownership over AI architecture
- Work on production-grade Agentic/Generative AI systems
- Exposure to LLMs, RAG, multi-agent architectures, LLMOps
Back to all jobs