AI Engineer

AI Engineer

Hyderabad Hybrid

Exp: 3+ yrs

About the Role We are seeking a skilled and experienced AI Engineer to join our team. In this role, you will be responsible for designing, developing, and deploying production-grade AI systems and intelligent agent pipelines. You will work at the intersection of software engineering and applied artificial intelligence, building scalable, reliable, and high-performance solutions.

Key Responsibilities

● Design and deploy production-ready Python services powering AI capabilities, leveraging FastAPI for robust API development.

● Architect and fine-tune end-to-end agent workflows supporting chat, search, and retrieval use cases. ● Develop intelligent agents using LangChain, LangGraph, and LangSmith, encompassing prompt engineering, integration, and comprehensive testing.

● Integrate and optimize vector databases (Qdrant, Milvus, etc.) for embeddings management, high-speed lookups, and hybrid search functionality.

● Continuously evaluate and monitor agent performance to ensure reliability, accuracy, and consistency in production environments.

● Optimize agent systems for reduced latency, cost efficiency, and horizontal scalability.

Required Qualifications

● 3+ years of total software engineering experience, with a strong foundation in backend development using Python.

● 1–2+ years of hands-on experience deploying and maintaining ML/AI systems in production environments (beyond research or proof-of-concept stages).

● Demonstrated proficiency in Python and software engineering best practices, with a focus on clean, maintainable, and production-quality code.

● Solid experience with NLP, Retrieval-Augmented Generation (RAG), embeddings, and vector databases such as Qdrant and Milvus.

● Deep expertise in LangChain and/or LlamaIndex for building agentic AI systems.

● Strong experience with Langsmith, understanding Evaluation Benchmarking and Tracing

● Proven experience in prompt engineering and systematic agent testing methodologies.

● Strong understanding of LLM inference pipelines, both on local infrastructure and cloud platforms.

● Proficiency with Docker and cloud platforms (AWS, GCP, or Azure).

● Demonstrated ability to design clean, well-documented APIs and integrate seamlessly with existing backend systems using a microservices architecture.