We are looking for an exceptional AI Software Engineer with proven expertise in developing autonomous, agentic AI applications that extend well beyond basic prompt engineering. The ideal candidate will have hands-on experience building production-quality systems capable of reasoning, planning, taking action, writing and debugging code, utilizing tools, integrating APIs, and continuously learning. In this role, you will lead the end-to-end development of intelligent AI systems, working at the intersection of large language models (LLMs), reasoning engines, memory architectures, retrieval-augmented generation (RAG), vector databases, tool orchestration, and scalable backend infrastructure. This position is ideal for someone passionate about advancing AI capabilities beyond conversational interfaces.
Key Responsibilities
- Architect, develop, and scale agentic AI applications leveraging foundation models such as OpenAI and Claude.
- Design complex systems that integrate RAG, tool usage, long-term memory, strategic planning, and multi-step task execution.
- Develop and maintain integrations with APIs, developer tools, and data platforms including GitHub, Jira, Slack, CRMs, and various databases.
- Build custom orchestration layers to enable multi-agent collaboration, continuous learning, and task decomposition.
- Optimize system performance with a focus on latency, cost-efficiency, and reliability in production environments.
- Evaluate, fine-tune, and perform prompt engineering on foundation models tailored to specific use cases.
- Stay up to date with the latest advancements in LLM capabilities, agent frameworks, embedding techniques, and architectural patterns.
- Collaborate closely with product managers, designers, and domain experts to deliver exceptional AI-first user experiences.
Required Qualifications
- Proven experience building operational agentic AI systems rather than simple GPT wrappers.
- Proficiency in Python, TypeScript, LangChain, LLM APIs, and vector databases such as Pinecone or Weaviate.
- Strong understanding of transformer models, tokenization processes, and techniques to maximize LLM performance.
- Experience designing and implementing backend systems and scalable cloud infrastructure using platforms like AWS, GCP, and containerization tools such as Docker.
- Ability to architect complex asynchronous workflows and memory management systems.
- A hacker mindset characterized by speed, efficiency, and a focus on real-world performance and impact.
Preferred Qualifications and Benefits
- Contributions to open-source agentic AI projects or publication of notable AI experiments.
- Experience with real-time collaborative tools, browser automation, or integrations with developer tools is a plus.
- Opportunity to work alongside founders and engineers with deep AI expertise.
- Chance to build innovative products that transform how people work, create, and think.
- Fast-paced startup environment that values rapid shipping, long-term vision, and technical excellence.
- Join at the ground floor of an AI-native company with significant growth potential.
Job Type: Full-time
Compensation: Rs40,000 - Rs50,000 per month
Location: Remote