Experience: 3–4 Years | Location: Pune
Work Mode: Hybrid | Employment Type: Full-time
Key Responsibilities:
- Design, prototype, and deploy AI/LLM-enabled applications with a focus on scalability and maintainability.
- Develop and fine-tune RAG pipelines for enterprise or product-based use cases, ensuring high retrieval relevance and accuracy.
- Work with unstructured data (documents, transcripts, APIs) and transform it into structured knowledge systems using embeddings, vector stores, and knowledge graphs.
- Evaluate and select GenAI tools, frameworks, and models, balancing performance, latency, cost, and security.
- Monitor and refine prompts, retrieval logic, and context engineering to enhance response quality.
- Identify and communicate system risks such as hallucination, bias, and prompt injection.
- Stay updated on cutting-edge AI research and assess practical applications for production.
- Collaborate with cross-functional teams to integrate intelligent features seamlessly.
- Document technical decisions, limitations, and assumptions clearly.
Required Skills & Experience:
- 3–4 years in AI/ML, data engineering, or full-stack development.
- Strong understanding of Large Language Models (LLMs) — embeddings, context windows, transformers, token limits, and memory strategies.
- Proven experience with RAG pipelines, vector databases, and Knowledge Graphs.
- Familiarity with GenAI frameworks (e.g., LangChain, LlamaIndex).
- Proficiency in Python and API integration.
- Awareness of AI ethics, safety, and fairness.
- Ability to assess trade-offs in system design (cloud vs. edge, fine-tuning vs. prompt engineering, open vs. closed models).
Job Type: Full-time
Work Location: In person