Summary:

- We are looking for a skilled AI Engineer with hands-on experience in AI model evaluation, LLM-based applications, autonomous AI agents, and workflow automation.
- The candidate will be responsible for evaluating AI systems, developing intelligent automation solutions, and improving overall AI performance and reliability.

Key Responsibilities

- Conduct AI model evaluation, benchmarking, testing, and quality assessments.
- Develop and implement autonomous AI agents and automated workflows.
- Build, integrate, and maintain AI-powered applications using Python.
- Design LLM evaluation pipelines, prompt engineering workflows, and feedback mechanisms.
- Automate AI training and evaluation processes to improve efficiency.
- Troubleshoot technical issues, optimize AI systems, and maintain documentation.
- Collaborate on AI development, testing, and continuous improvement.

Required Skills

- Solid Python programming skills with experience in AI development.
- Hands-on experience with LLMs,



AI model evaluation, and benchmarking.
- Experience developing AI agents using LangChain, LangGraph, CrewAI, or similar frameworks.
- Knowledge of prompt engineering, API integrations, and workflow automation.
- Understanding of machine learning fundamentals, AI testing, and quality assurance.
- Familiarity with Git and software development practices.

Preferred Skills

- Experience with AI training and evaluation platforms.
- Knowledge of RAG, vector databases, or model fine-tuning.
- Experience building automated AI testing and evaluation pipelines.
- Familiarity with cloud infrastructure and AI deployment.

Qualifications

- Bachelor's degree in Computer Science, AI, Data Science, or a related field.
- 2–5 years of relevant experience in AI/ML development, LLM applications, or AI automation.

📌 AI Engineer - Model Training, Evaluation & Automation (Kolkata)
🏢 UpTye
📍 Kolkata