Artificial Intelligence Engineer

We are seeking an experienced AI Developer (4–6 years) skilled in applying Large Language Models (LLMs) and building AI-driven applications to join our growing team. A significant part of this role involves designing and developing AI Agents within our platform with an initial focus on integrating external LLM APIs(e.g., OpenAI, Anthropic, Google) via sophisticated prompt engineering and RAG techniques into these agents, built using Python + FastAPI.

You will architect the logic for these agents, enabling them to perform complex tasks within our e-commerce and retail data orchestration pipelines. Furthermore, as Ekyam.ai evolves, this role offers the potential to grow into customizing and deploying LLMs in-house, so adaptability and a strong foundation in ML/LLM principles are key.

Key Responsibilities

• AI Agent Development:

   Design, develop, test, and maintain the core logic for 

  AI Agents

   within 

  FastAPI

   services. Orchestrate agent tasks, manage state, interact with platform data/workflows, and integrate LLM capabilities.

• LLM API Integration & Prompt Engineering:

   Integrate with external 

  LLM provider APIs

  . Design, implement, and rigorously test effective 

  prompts

   for diverse retail-specific tasks (generation, Q&A, summarization).

• RAG Implementation:

   Implement and optimize 

  Retrieval-Augmented Generation (RAG)

   patterns using 

  vector databases

   to provide relevant context to LLM API calls made by agents.

• FastAPI Microservice Development:

   Build and maintain the scalable 

  FastAPI

   microservices that host AI Agent logic and handle interactions with LLMs and other platform components in a containerized environment (

  Docker, Kubernetes

  ).

• Data Processing for AI:

   Prepare and preprocess data required for effective prompt context, RAG retrieval, and potentially for future fine-tuning tasks.

• Collaboration & Future Adaptation:

   Work with cross-functional teams to deliver AI features. Stay updated on LLM advancements and be prepared to learn and contribute to potential future in-house LLM fine-tuning and deployment efforts.

Required Skills & Qualifications

• 4–6 years

   of hands-on experience in software development with a strong focus on 

  AI/ML application development

  .
• Demonstrable experience 

  integrating and utilizing external LLM APIs

   (e.g., OpenAI, Anthropic, Google) in applications.
• Proven experience with 

  Prompt Engineering

   techniques.
• Strong 

  Python

   programming skills.
• Practical experience building and deploying 

  RESTful APIs

   using 

  FastAPI

  .
• Experience designing and implementing application logic for 

  AI-driven features or agents

  .
• Understanding and practical experience with 

  RAG

   concepts and 

  vector databases

   (Pinecone, FAISS, etc.).
• Solid understanding of core 

  Machine Learning concepts

   and familiarity with frameworks like 

  PyTorch, TensorFlow, or Hugging Face

   (important for understanding models and future adaptation).
• Familiarity with 

  cloud platforms

   (

  AWS, GCP, or Azure

  ) and containerization (

  Docker, Kubernetes

  ) for application deployment.
• Solid problem-solving skills and clear communication abilities.
• Experience working effectively in an 

  agile

   environment.

• Willingness and capacity to learn and adapt

   towards future work involving deeper LLM customization and deployment.
• Bachelor's or Master's degree in Computer Science, AI, or a related field.
• Ability to work independently and collaborate effectively in a remote setting.

Preferred Qualifications

• Experience with frameworks like 

  LangChain

   or LlamaIndex.
• Experience with observability and debugging tools for LLM applications, such as 

  LangSmith.

• Experience with graph databases (e.g., Neo4j) and query languages (e.g., Cypher).

• Experience with MLOps

   practices, applicable to both current application monitoring and future model lifecycle management.
• Experience optimizing API call performance (latency/cost) or model inference.
• Knowledge of 

  AI security

   considerations and 

  bias mitigation

  .