About the role
Key ResponsibilitiesAI/LLM Engineering
- Design, develop, and deploy end-to-end LLM-based applications, conversational agents, and automation workflows.
- Build prompt engineering strategies, evaluation workflows, and structured prompting for enterprise use cases.
- Implement RAG (Retrieval Augmented Generation) systems using vector databases such as Pinecone, FAISS, or ChromaDB.
- Fine-tune, evaluate, and optimize models (open-source or API-based LLMs).
- Build and deploy ML models for classification, NLP, prediction, and document processing.
- Work on data preprocessing, feature engineering, and model optimization.
- Integrate ML/LLM workflows using microservices, APIs, webhooks, and automation pipelines.
- Work with Python frameworks (FastAPI/Flask) to build scalable model-serving endpoints.
- Integrate AI systems with enterprise platforms, databases, and internal applications.
- Contribute to architecture decisions for LLM apps, agentic systems, and AI microservices.
- Collaborate with data scientists, product owners, and solution architects to deliver AI-powered features.
- Review code, mentor junior engineers, and set technical standards for AI development.
- Prepare documentation, reusable components, and best practices for AI implementation.
Required SkillsCore Skills
- Strong proficiency in Python (Pandas, NumPy, FastAPI/Flask, Async programming preferred).
- Hands-on experience with LLMs (OpenAI, Llama, Mistral, Claude, Qwen, etc.).
- Experience with LangChain, LlamaIndex, or Hugging Face.
- Strong understanding of RAG pipelines, embeddings, and vector search.
- Practical experience with vector databases: Pinecone, FAISS, Weaviate, or ChromaDB.
- Knowledge of REST APIs, JSON integrations, token-based authentication.
- Experience with Git, Docker, CI/CD workflows.
- Experience with NLP, classical ML, text preprocessing, and supervised learning.
- Ability to evaluate model performance and optimize latency & accuracy.
- Understanding of data pipelines and ETL workflows.
- Experience with at least one cloud platform (AWS/Azure/GCP).
- Familiarity with Kubernetes, model deployment, or container orchestration (nice to have).
Nice-to-Have Skills
- Experience with agentic AI frameworks (AutoGen, CrewAI, LangGraph, Swarm, etc.).
- Exposure to MLOps tools (MLflow, Airflow, Weights & Biases).
- Knowledge of front-end AI app integration (Streamlit, Gradio, or React).
- Understanding of AI security, governance, and responsible AI principles.
Qualifications
- Bachelor’s or Master’s degree in Computer Science, AI/ML, Data Science, or related field.
- 3–5 years of hands-on experience in AI/ML or LLM engineering.
- Previous project or product development experience in NLP/LLM highly preferred.
What We Offer
- Opportunity to work on cutting-edge AI/LLM technologies.
- Exposure to enterprise-grade AI architectures, RAG systems, and agentic workflows.
- Mentorship from senior architects and a collaborative engineering culture.
- Innovation-driven environment with continuous learning opportunities.