Key Responsibilities
- Design complex prompt strategies (Chain-of-Thought, Few-Shot, ReAct) for high-quality LLM outputs.
- Optimize system prompts to reduce hallucinations, improve tone consistency, and manage token usage.
- Build automated evaluation pipelines to benchmark prompt performance against ground-truth datasets.
- Develop, deploy, and maintain scalable RESTful APIs using FastAPI.
- Integrate LLM providers, MongoDB databases, and 3rd-party tools into application workflows.
- Implement async execution and caching to reduce latency and improve response times.
Must-Haves
- Bachelor's degree in computer science, IT, or related technical field.
- 2+ years of experience in software development or AI application engineering.
- Strong Python skills with FastAPI or Flask.
- Experience using LLM APIs (OpenAI, Anthropic, etc.) and understanding parameters (Temperature, Top-P, context windows).
- Hands-on experience with MongoDB and NoSQL data modeling.
- Solid understanding of RESTful API principles and HTTP standards.
- Proficient with Git/GitHub.
Nice-to-Haves
- Experience with LangChain or OpenAI Agents SDK.
- Familiarity with vector databases (Milvus, Pinecone, Qdrant) for RAG pipelines.
- Experience writing unit tests (pytest) for AI systems.
- Basic understanding of Docker/containerization.
Job Types: Full-time, Permanent
Pay: ₹11,262.66 - ₹35,000.00 per month
Work Location: In person