Generative AI Engineer

Key Responsibilities:

• Design and develop GenAI applications leveraging LLMs (OpenAI, Anthropic, LLaMA, Mistral, etc.) and frameworks.
• Build and optimize RAG pipelines using vector databases (Pinecone, Weaviate, FAISS, Milvus, Chroma).
• Implement prompt engineering, fine-tuning, and model evaluation to improve accuracy and business relevance.
• Develop and deploy AI agents, copilots, and workflow automation using multi-agent frameworks like LangGraph or Agno
• Work with cloud platforms (AWS, Azure, GCP) to scale GenAI applications securely.
• Integrate AI models into enterprise systems via APIs, microservices, or SDKs.
• Research emerging AI models and frameworks to continuously improve solution quality.
• Ensure solutions meet compliance, explainability, and ethical AI standards.

Key Skills & Qualifications:

• Strong programming skills in Python (must-have), with experience in Node.js/Java as a plus.
• Hands-on experience with GenAI frameworks (LangChain, Haystack, LlamaIndex, RAG setups).
• Experience with fine-tuning and evaluating LLMs (Hugging Face, OpenAI, Mistral, etc.).
• Knowledge of vector databases (Pinecone, FAISS, Weaviate, Milvus, Chroma).
• Cloud deployment experience on AWS (SageMaker, Bedrock), Azure (OpenAI Service), or GCP (VertexAI).
• Understanding of MLOps for GenAI – CI/CD pipelines, model monitoring, retraining.
• Familiarity with multi-agent frameworks and conversational AI design.
• Strong problem-solving skills, with ability to translate business use cases into AI solutions.

Nice to Have:

• Experience in finance domain AI use cases (fraud detection, credit risk, compliance copilots, reporting automation).
• Exposure to speech-to-text (Whisper, Deepgram) and multimodal AI.
• Understanding of data engineering pipelines and ETL for AI.