Match Score
Against your primary resumeLogin to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Protocol Intelligence
Data-driven signals on your job's competitivenessLog in to see why each signal reads the way it does.
Job Description
Structured overview of role & requirementsAbout This Role
Build and integrate LLM-powered features and AI workflows into production applications.
Develop and optimize Retrieval-Augmented Generation (RAG) systems and embedding-based semantic search solutions.
Design and improve prompts, evaluate LLM responses, and manage APIs/backend services using Python.
Minimum Requirements
1–2 years of experience in software development, AI/ML, or Generative AI with hands-on LLM API experience (OpenAI, Gemini, Anthropic, or open-source).
Strong programming skills in Python and practical knowledge of prompt engineering, RAG, embeddings, vector databases, and REST APIs.
Familiarity with Git/GitHub, problem-solving, debugging, and ability to build AI features from prototype to production.
Work Experience Required: 1–2 years in relevant fields.
Ideal Candidate Profile
Has built real LLM/Generative AI projects from idea to working prototype beyond coursework.
Understands production complexities including hallucination mitigation, retrieval accuracy, and performance trade-offs.
Comfortable experimenting with multiple LLM models, prompt designs, and AI technologies to improve feature reliability.