AI Engineer

Integrate and orchestrate OpenAI, Gemini, and other LLM APIs to power features such as:

Essay & Recommendation Brainstorming (Voice & Text)

AI-driven Evaluation and Scoring

Contextual, voice-based guidance via Ivy (Text-to-Speech + prompt control)

Build and fine-tune prompt-response workflows , input-output schemas, fallback handling, and session management.

Convert speech inputs to structured text using Speech-to-Text APIs , and implement Text-to-Speech outputs for voice-based interactions.

Set up and manage Vector Databases (e.g., Pinecone, Weaviate, AstraDB) to store and retrieve semantically indexed essay data.

Collaborate with backend, frontend, and QA teams to ensure smooth flow of AI-driven features across the platform.

Evaluate and continuously improve AI output quality by testing prompt variations and refining scoring logic.

Requirements Mandatory Requirements:

1\u20131.5 years of hands-on experience building with LLM APIs (OpenAI, Gemini, Claude, etc.)

Strong grasp of prompt engineering , including role prompting, temperature control, and context design

Experience working with Python and integrating APIs in live products

Familiarity with Text-to-Speech and Speech-to-Text workflows (OpenAI Whisper, Google Cloud STT/TTS, etc.)

Exposure to using or querying Vector Databases (e.g., Pinecone or similar)

Basic understanding of AI evaluation techniques (prompt tuning, hallucination handling, response scoring
Good to Have:

Experience with LangChain , LlamaIndex , or agent frameworks

Working knowledge of FastAPI or Django to support backend integration

Familiarity with Voice UX or chatbot design

Comfort with versioning tools (Git), JSON handling, and API testing tools (Postman)

Demonstrated ability to iterate quickly and adapt to changing LLM capabilities