Job
Description

Job Description

We are looking for an AI / Generative AI Engineer with approximately 3 years of experience building production-oriented LLM applications, RAG systems, and agentic workflows. The candidate should be capable of independently owning AI modules from design through API development, testing, and cloud deployment.

Key Responsibilities

• Design and develop production-grade Generative AI and LLM applications.
• Build RAG systems with embeddings, semantic retrieval, vector databases, and knowledge grounding.
• Develop agentic workflows using LangChain and LangGraph, including routing, tool calling, and task orchestration.
• Integrate LLMs with enterprise data, databases, APIs, and external tools.
• Design prompt strategies and structured output pipelines for reliable business use cases.
• Develop scalable backend services and REST APIs using FastAPI or Flask.
• Deploy and integrate AI workloads using AWS Lambda, S3, SQS, and EC2.
• Implement testing and validation strategies for non-deterministic LLM outputs, including regression checks.
• Translate business requirements into technical AI workflows and independently own assigned modules.
• Collaborate with engineering, data, product, and business teams.

Mandatory Skills

• 3 years of relevant experience in AI, Data Science, Generative AI, or software engineering.
• Strong Python and SQL skills.
• Hands-on experience with LLM application development and RAG.
• Strong working knowledge of LangChain and practical exposure to LangGraph.
• Experience with vector databases such as Pinecone, FAISS, or Chroma.
• Experience developing REST APIs using FastAPI or Flask.
• Practical AWS experience, preferably Lambda, S3, SQS, and EC2.
• Understanding of LLM evaluation, structured outputs, and production reliability.

Preferred Background

Experience with multi-agent workflows and agent collaboration; OpenAI, Anthropic, Llama, Groq, or similar models; enterprise document processing and information extraction; PostgreSQL, MySQL, MongoDB, or MSSQL; and exposure to Streamlit, ECharts, or AI-driven dashboards. Candidates should demonstrate practical implementation capability rather than purely theoretical knowledge.