Generative AI Engineer

Key Responsibilities

● LLM Orchestration: Design and deploy sophisticated LLM-based applications using

frameworks such as LangChain, LlamaIndex, or Semantic Kernel.

● Model Optimization: Lead the fine-tuning of open-source and proprietary models to

improve performance, latency, and cost-efficiency.

● Advanced RAG Systems: Architect and optimize Retrieval-Augmented Generation (RAG)

pipelines utilizing vector databases like Pinecone, FAISS, Weaviate, or Azure AI Search.

● Scalable Deployment: Containerize services using Docker and deploy via FastAPI and Azure

Functions to ensure high availability and low latency.

● Productization: Build and scale enterprise-grade chatbots, copilots, and automated content

generation tools using OpenAI/Azure OpenAI and Hugging Face.

● Prompt Engineering: Implement and manage advanced prompt optimization and versioning

workflows to enhance model accuracy.

● Monitoring & Evaluation: Establish robust evaluation frameworks (e.g., RAGAS, TruLens) to

track model performance, hallucination rates, and drift in production.

● Operationalization: Collaborate with cross-functional teams (Product, DevOps, Data) to

identify high-impact use cases and move them from POC to production.

● Best Practices: Set the standard for GenAI engineering, including model selection criteria,

performance tracking, and ethical AI safeguards.

Required Skills & Qualifications

● Overall Experience: 3 to 6 years of professional software engineering experience.

● GenAI Domain Experience: 2 years of dedicated, hands-on experience building GenAI, LLM,

and OCR solutions in production environments.

● Programming Mastery: Deep proficiency in Python with expertise in asynchronous

programming, typing standards, and clean code principles.

● Generative AI & LLMs: Hands-on experience with commercial APIs (OpenAI GPT-4o,

Anthropic Claude, Azure OpenAI) and open-source models (Llama 3, Mistral), along with

modern agentic frameworks.

● Vector Infrastructure & Search: Practical experience with hybrid search (dense + sparse), re-

ranking algorithms, metadata filtering, and vector index tuning.

● Backend & Cloud: Strong background in FastAPI, Docker, Git, CI/CD pipelines, and

enterprise cloud ecosystems (Azure / AWS).

● Problem Solving: Proven track record of solving hallucination, context window limitations,

and data grounding issues in production.