About the role
- 4–6 years of overall software engineering or ML experience.
- 2+ years of hands-on experience in Generative AI, LLMs, or applied NLP.
- Strong programming skills in Python (required); experience with JavaScript/TypeScript is a plus.
- Practical experience with:
- LLM APIs and frameworks (e.g., OpenAI-compatible APIs, LangChain, LlamaIndex)
- Prompt engineering and RAG architectures
- Vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma)
- Experience deploying ML/AI solutions in cloud environments (AWS, Azure, or GCP).
- Solid understanding of data structures, APIs, and system design.
- Ability to write clean, maintainable, and testable code.
- Design, develop, and deploy Generative AI applications using LLMs (e.g., GPT-based, open-source models).
- Build and optimize prompt engineering, RAG (Retrieval-Augmented Generation), and fine-tuning pipelines.
- Integrate GenAI models into production systems using APIs, microservices, and cloud platforms.
- Collaborate with product managers, data scientists, and backend engineers to translate business needs into AI-driven solutions.
- Evaluate model performance, mitigate hallucinations, and improve accuracy, safety, and latency.
- Implement monitoring, logging, and feedback loops for continuous model improvement.
- Stay current with emerging GenAI frameworks, tools, and best practices.
- Ensure compliance with security, privacy, and responsible AI guidelines.
- Experience in RAG based applications using LangGraph and FastAPI.
- Familiarity with MLOps practices (CI/CD for ML, model versioning, monitoring).
- Knowledge of NLP concepts such as embeddings, transformers, and tokenization.