Associate Engineer

Key Responsibilities: Design and develop LLM-based applications such as chatbots, document Q&A systems, and AI assistants. Implement Retrieval-Augmented Generation (RAG) pipelines including chunking, embedding generation, vector storage, and response grounding. Integrate LLM APIs with function calling, streaming, and structured output handling into backend services.

Build and expose RESTful APIs using FastAPI; contribute to containerized deployments using Docker/Podman. Leverage AI-assisted development tools (e.g., GitHub Copilot, Cursor, Claude Code) as a core part of the engineering workflow. Participate in code reviews, maintain clean and modular codebases, and adhere to engineering best practices.

Stay current with advancements in Generative AI, LLMs, and the broader AI engineering ecosystem. Required Qualifications: AI & LLM Skills: Understanding of Large Language Model fundamentals - architecture, context management, and inference parameters Experience with prompt engineering techniques including chain-of-thought, few-shot prompting, and system prompt design Familiarity with Retrieval-Augmented Generation (RAG) - retrieval strategies, chunking, and response grounding Exposure to agentic AI patterns - tool use, memory management, and multi-agent orchestration Awareness of LLM limitations such as hallucinations, prompt injection, and context degradation Proficiency in vibe coding tools (e.g., GitHub Copilot, Cursor, Claude code etc). Programming & Technical Skills: Strong proficiency in Python - including asynchronous programming, modular design, and clean code practices Hands-on experience with LLM application frameworks such as LangChain, LangGraph, or LlamaIndex Familiarity with LLM API integration - function calling, streaming, and structured output handling Ability to build and expose backend services using FastAPI; understanding of containerization (Docker/Podman) Proficient with Git, Linux environments, and foundational cloud services (GCP / AWS / Azure) Good to Have: Solid grounding in core ML concepts - supervised and unsupervised learning, model evaluation metrics, regularization, and optimization Hands-on exposure to deep learning using PyTorch or TensorFlow; conceptual understanding of LLM fine-tuning methodologies Familiarity of Natural Language Processing - tokenization, word and sentence embeddings, and semantic similarity measures Statistical Reasoning - probability, distributions, hypothesis testing, and the ability to interpret and reason over insights and data meaningfully