About the role
Responsibilities:
- Design and develop production-grade AI applications using Python.
- Build autonomous AI agents and Agentic AI workflows for enterprise use cases.
- Develop and optimise enterprise-grade RAG pipelines for intelligent document and data processing.
- Integrate Large Language Models into scalable business applications.
- Design and implement multi-agent systems and agent orchestration frameworks.
- Optimise AI systems for performance, scalability, reliability, and cost efficiency.
- Implement AI monitoring, evaluation, and feedback loops for continuous improvement.
- Collaborate with Product, Backend, and DevOps teams to deliver production-ready AI solutions.
- Stay current on emerging LLM, agent, and GenAI technologies and best practices.
Requirements:
- 3.6-5 years of experience in AI Engineering, ML Engineering, or Backend Development.
- Agentic AI experience: Mandatory hands-on building and deploying autonomous AI agents in production.
- Strong proficiency in Python (Mandatory).
- Must have independently built or been a key contributor in developing AI agents using LangGraph, LangChain, LlamaIndex, CrewAI, or AutoGen.
- Deep understanding of RAG architectures, vector search, embeddings, and document pipelines.
- Experience with LLM APIs: OpenAI, Anthropic, Gemini, or similar.
- Hands-on with Vector Databases: Pinecone, Chroma, Weaviate, or pgvector.
- Strong understanding of Prompt Engineering and LLM optimisation techniques.
- Experience building REST APIs and backend services to support AI systems.
- Experience with multi-agent orchestration and autonomous workflow design.
Good to Have:
- Experience with MCP (Model Context Protocol).
- Familiarity with LLM evaluation tools Ragas, LangSmith, or similar.
- Exposure to MLOps and LLMOps practices.
- Experience with Docker, Kubernetes, or CI/CD pipelines.
- Cloud platform experience: AWS, GCP, or Azure.
- Familiarity with fine-tuning or RLHF techniques.
- Open-source AI contributions or public AI portfolio.