Title: LLM Engineer / Generative AI Engineer
Location: Gurgaon, Haryana (Onsite/Hybrid)
Experience:
- 4-6 years of experience in Software Engineering, Machine Learning, or AI, with at least 1 year of hands-on experience building LLM-based applications.
About the Role:
We are looking for an experienced LLM Engineer / Generative AI Engineer to design, develop, and deploy production-grade Generative AI applications powered by Large Language Models (LLMs). The ideal candidate will have hands-on experience with prompt engineering, Retrieval-Augmented Generation (RAG), fine-tuning, vector databases, and deploying scalable AI solutions in cloud environments.
Key Responsibilities:
- Design, develop, and deploy LLM-powered applications using models such as GPT-4, Claude, Gemini, Llama, Mistral, and other open-source LLMs.
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines using LangChain and LlamaIndex.
- Develop prompt engineering strategies and fine-tune open-source models using LoRA, QLoRA, and PEFT techniques.
- Implement semantic search solutions using Pinecone, Weaviate, FAISS, or ChromaDB.
- Deploy and manage AI applications using Docker, Kubernetes, FastAPI, and cloud platforms (AWS, GCP, or Azure).
- Build evaluation frameworks to measure model accuracy, hallucinations, latency, safety, and overall performance.
- Collaborate with Product, Data Science, and Engineering teams to integrate Generative AI capabilities into business applications.
Required Skills:
- 4-6 years of experience in Software Engineering, Machine Learning, or AI, with at least 1 year of hands-on experience building LLM-based applications.
- Strong proficiency in Python, FastAPI, Flask, and asynchronous programming.
- Experience with LangChain, LlamaIndex, OpenAI API, Hugging Face Transformers, and modern LLM frameworks.
- Hands-on experience with LoRA, QLoRA, PEFT, and open-source models such as Llama 2/3, Mistral, or Phi.
- Experience with Vector Databases including Pinecone, Weaviate, ChromaDB, or FAISS.
- Knowledge of embedding models such as OpenAI, Cohere, or Hugging Face Embeddings.
- Experience with AWS, GCP, or Azure, along with Docker, Kubernetes, Git, and deployment best practices.
- Strong understanding of SQL and working with structured and unstructured text data.
Preferred Skills:
- Experience with AI Agent frameworks such as CrewAI, AutoGen, or similar.
- Knowledge of LLM guardrails, AI safety, hallucination mitigation, and cost optimization.
- Experience building multimodal AI applications involving text and vision models.
- Familiarity with MLOps, CI/CD pipelines, and model monitoring.
Qualifications:
- Bachelor's or Master's degree (B.Tech/M.Tech) in Computer Science, Artificial Intelligence, Data Science, or a related field.
- Proven experience deploying LLM-based applications in production environments.
- Excellent analytical, problem-solving, and communication skills.
