Key Responsibilities :

- Design, develop, and deploy intelligent AI agents using LangChain, LlamaIndex, AutoGen, or custom agent architectures.

- Build production-ready Generative AI applications using LLMs and foundation models such as GPT, Claude, Llama, and Mistral.

- Develop and optimize prompt engineering strategies for accuracy, reliability, and cost efficiency.

- Implement Retrieval-Augmented Generation (RAG), embeddings, vector search, and knowledge-based AI solutions.

- Perform model selection, fine-tuning, inference optimization, and evaluation based on business requirements.

- Integrate AI solutions with enterprise applications using REST/gRPC APIs, microservices, and event-driven architectures.

- Implement AI observability, evaluation, testing, and governance using tools such as LangSmith, PromptLayer, Weights & Biases, or Arize.

- Deploy and scale AI applications using Docker, Kubernetes, and infrastructure-as-code tools such as Terraform or AWS CDK.

- Collaborate with product, data, and DevOps teams to deliver secure, scalable, and responsible AI solutions.

- Monitor production AI systems, troubleshoot issues, and continuously improve model performance and reliability.

Required Skillsets :

- 5+ years of experience in AI engineering, software development, or related fields, with strong hands-on experience in Generative AI.

- Strong programming skills in Python and experience building production-grade applications.

- Hands-on experience with LLMs, prompt engineering, RAG, embeddings, and vector databases.

- Experience developing AI agents using LangChain, LlamaIndex, AutoGen, or similar frameworks.

- Understanding of LLM fine-tuning, model evaluation, inference optimization, and tool-calling capabilities.

- Experience integrating AI models through APIs, microservices, and event-driven systems.

- Knowledge of Docker, Kubernetes, CI/CD, and infrastructure-as-code practices.

- Familiarity with AI observability, tracing, testing, monitoring, and governance tools.

- Strong understanding of application security, data privacy, responsible AI, and production deployment practices.