Generative AI Engineer

Job Responsibilities

AI Application Development – Design and orchestrate intelligent systems using modern generative and agentic AI frameworks; implement retrieval-augmented and fine-tuned model pipelines.
Model Engineering – Integrate and customize large language models; design structured prompts, evaluation logic, and lightweight tuning workflows to enhance contextual accuracy, speed, and cost.
API & Service Deployment – Develop scalable REST / FastAPI services, containerize them for cloud deployment, and apply MLOps best practices for versioning and monitoring.
Data & Vector Pipelines – Develop embedding pipelines, manage vector databases, and collaborate with data engineers for preprocessing and retrieval optimization.

Programming & ML Foundations: Proficiency in Python with knowledge of data handling, ML pipelines, and deep-learning concepts.
Generative AI Frameworks: Experience with LangChain / LangGraph / CrewAI / DSPy, or similar agentic toolkits.
Vector Databases & Retrieval: Practical use of Milvus / Pinecone / ChromaDB / FAISS, or Azure AI Search for contextual search and embeddings.
Cloud & Deployment: Exposure to Azure OpenAI, AWS Bedrock, or Vertex AI; containerization with Docker / Kubernetes; CI/CD using GitHub or Azure DevOps.
MLOps & Monitoring: Familiar with MLFlow / Arize Phoenix / Weights & Biases, or equivalent tools for model tracking and observability.
Prompt & Model Evaluation: Ability to design and test prompt templates using structured evaluation frameworks like AgentEval / DeepEval for quantitative and qualitative assessment.

Nice to Have

Bachelor’s degree in Computer Science, AI/ML, or related field.
Experience building LLM-based assistants or retrieval systems.
Familiarity with Cursor, Claude Code or AI-assisted development environments.
Contributions to open-source AI/ML projects or applied research.
Understanding of Responsible AI, data privacy, and model governance.