About the Role:
- Design, develop, and deploy autonomous AI agents capable of reasoning, memory retention, and tool usage.
- Build multi-agent systems integrated with APIs, databases, and third-party services.
- Implement Retrieval-Augmented Generation (RAG) pipelines and optimize AI workflows.
- Collaborate with cross-functional teams to ensure scalable, reliable, and secure AI solutions.
Key Responsibilities:
- Architect and develop AI agents using modern LLM frameworks.
- Manage multi-agent interactions, reasoning processes, and persistent memory.
- Integrate AI systems with external APIs, vector databases, and cloud services.
- Optimize prompts, agent workflows, and model performance.
- Ensure robust, production-ready deployments with scalability and security in mind.
Required Skills & Qualifications:
- 3+ years of Python and backend development experience.
- Hands-on experience with LLMs and agentic AI frameworks (LangChain, LlamaIndex, AutoGen).
- Knowledge of vector databases (Pinecone, FAISS, Weaviate).
- Strong understanding of RAG, embeddings, and AI workflows.
- Familiarity with REST APIs, microservices, and cloud platforms (AWS, GCP, Azure).
- Experience with Docker and CI/CD pipelines.
Education:
- BE/BTech in CS, AI, IT, or related field OR
- MSc IT / MSc AI or equivalent postgraduate degree
Good to Have:
- Experience fine-tuning or customizing LLMs.
- Knowledge of AI evaluation, safety, and guardrails.
- Experience building AI copilots or automation agents.
Why Join:
- Work on cutting-edge agentic AI and autonomous systems.
- High-impact projects with real-world AI applications.
- Opportunities for strong learning and career growth.
