Role:
AI Developer
Type:
Full-Time (Payroll)
Location:
Remote (UK Shift)
Reports To:
Head of AI / Engineering Lead
Experience:
4 to 6 Years
Compensation:
?12 25 Lakh / Year
Availability:
Immediate Joiners Only
Role Overview
We are seeking an experienced AI Developer with strong expertise in Large Language Models (LLMs) and AI-driven application development to join our fast-growing team at Ekyam.ai.In this role, you will design and build AI Agents within our platform, leveraging LLM APIs (OpenAI, Anthropic, Google, etc.), prompt engineering, and RAG (Retrieval-Augmented Generation) techniques. You will be responsible for architecting agent logic, enabling complex tasks within e-commerce and retail data orchestration pipelines.
Responsibilities
This role also offers growth opportunities to work on in-house LLM customization and deployment, making it an ideal opportunity for AI professionals eager to evolve with cutting-edge AI Responsibilities :
- AI Agent Development: Design, implement, test, and maintain AI Agent logic within FastAPI microservices, enabling intelligent orchestration of platform tasks and workflows.
- LLM API Integration & Prompt Engineering: Connect with external LLM APIs, craft and optimize prompts, and ensure robust performance for use cases such as summarization, Q&A, and content generation.
- RAG Implementation: Implement Retrieval-Augmented Generation pipelines with vector databases (Pinecone, FAISS, Weaviate, etc.) to enhance LLM responses with contextual data.
- FastAPI Microservice Development: Build, deploy, and maintain scalable microservices in a containerized environment (Docker, Kubernetes) for AI agents.
- Data Processing for AI: Prepare, preprocess, and manage data pipelines for context retrieval, training, or fine-tuning purposes.
- Cross-Team Collaboration: Work with product, engineering, and data teams to deliver AI-powered features.
- Continuous Learning & Future Growth: Stay current with the latest advancements in LLMs, and contribute towards future LLM fine-tuning, deployment, and MLOps Skills & Qualifications :
- 4 to 6 years of hands-on experience in AI/ML application development.
- Strong programming skills in Python.
- Experience with FastAPI and REST API development.
- Proven experience integrating and working with LLM APIs (OpenAI, Anthropic, Google).
- Prompt Engineering expertise with demonstrable real-world use cases.
- Practical experience with RAG concepts and vector databases (Pinecone, FAISS, etc.).
- Solid understanding of Machine Learning fundamentals; exposure to PyTorch, TensorFlow, Hugging Face.
- Experience with cloud platforms (AWS, GCP, Azure) and containerized deployments (Docker, Kubernetes).
- Excellent problem-solving, debugging, and communication skills.
- Ability to thrive in an agile, remote-first environment.
- Bachelors or Masters in Computer Science, AI, or related Qualifications :
- Experience with LangChain or LlamaIndex for AI agent development.
- Familiarity with LangSmith for observability and debugging AI pipelines.
- Experience with graph databases (Neo4j, Cypher).
- Knowledge of MLOps practices, including model lifecycle management.
- Skills in optimizing LLM performance (latency/cost).
- Awareness of AI security and bias mitigation best Skills Summary :
- Python (3+ Years) Intermediate
- FastAPI (1+ Years) Intermediate
- LLM (1+ Years) Intermediate
- Prompt Engineering (1+ Years) Intermediate
- Generative AI (2+ Years) Intermediate
- Artificial Intelligence (2+ Years) Intermediate
(ref:hirist.tech)