Generative AI Engineer (Hands-on Development Role)
Location: Winfo Solutions
Job Type: Full-time
Experience: 6-10 years
Industry: IT Consulting
About The Role
We are looking for a Generative AI Engineer with strong software engineering skills and hands-on experience in developing AI-powered applications. This role involves coding AI-driven solutions, developing APIs, integrating models into products, and building scalable AI systems for production use.
Key Responsibilities
Develop AI-driven applications by integrating LLMs and generative models into real-world software solutions.
Design and build APIs for LLMs and GenAI models (FastAPI, Flask, Django).
Write production-ready code to integrate AI features into web applications, chatbots, document processing tools, and recommendation systems.
Fine-tune and optimize LLMs (GPT, LLaMA, Gemini, Claude, Mistral) for performance in real-time applications.
Develop AI-powered chatbots, document extraction tools, and automation systems using LangChain, Haystack, or Semantic Kernel.
Implement vector search using FAISS, ChromaDB, or Pinecone for retrieval-augmented generation (RAG) applications.
Work with databases (PostgreSQL, MongoDB, Redis) to manage AI-driven data workflows.
Build scalable AI microservices and integrate them into enterprise applications.
Collaborate with backend engineers, data engineers, and DevOps teams to ensure seamless deployment of AI models.
Required Skills & Qualifications
Bachelor's or Master's in Computer Science, Software Engineering, AI, or related field.
6+ years of experience in software development, AI engineering, or full-stack AI application development.
Strong Python coding skills with experience in frameworks like FastAPI, Flask, Django.
Hands-on experience developing APIs for AI models and integrating them into real-world applications.
Experience with LLM APIs (OpenAI, Gemini, Claude, Mistral, etc.) and fine-tuning custom models.
Strong knowledge of vector databases (FAISS, ChromaDB, Pinecone) for AI-powered search.
Experience working with WebSockets, asynchronous programming, and RESTful APIs.
Database experience with PostgreSQL, MongoDB, or Redis for AI-driven applications.
Experience with MLOps pipelines (MLflow, Airflow, Prefect) for model retraining and monitoring.
Good To Have Skills & Qualifications
Familiarity with containerization (Docker, Kubernetes) and cloud-based AI deployments (AWS, GCP, Azure).
Basics of probabilistic models, deep learning techniques, NLP, and embeddings.
