We're seeking a senior AI Engineer with 5+ years of experience who thrives at the intersection of Generative AI, intelligent agents, and real-world application delivery.

You'll be responsible for designing, building, and deploying next-generation AI-powered systems that solve complex business problems - from automating workflows to creating intelligent decision-making agents.

This is not a research-only role.

You'll own the full lifecycle : ideation - prototyping - model selection - prompt engineering - integration - deployment - monitoring - all in production.

Roles and Responsibilities :

- Design and implement intelligent AI agents using frameworks like LangChain, LlamaIndex, AutoGen, or custom agent architectures.

- Develop and optimize prompt engineering strategies for accuracy, consistency, and cost efficiency across diverse use cases.

- Work with large language models (LLMs) and foundation models (e.g., Llama, Mistral, GPT, Claude) - fine-tuning, RAG, and inference optimization.

- Leverage MCP (Model Control Platforms) tools (e.g., PromptLayer, Weights & Biases, Arize, LangSmith) for observability, testing, and governance.

- Build cloud-agnostic AI pipelines using containerization (Docker), orchestration (K8s), and infrastructure-as-code (Terraform/CDK).

- Integrate AI components into existing systems using REST/gRPC APIs, event-driven architectures, and microservices.

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

- Stay ahead of the curve: evaluate new models, tools, and frameworks (e.g., multimodal AI, reasoning models, tool use).

Key Skills :

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

- Hands-on experience with Generative AI, LLMs, and foundation models such as GPT, Claude, Llama, and Mistral.

- Proficiency in AI agent frameworks such as LangChain, LlamaIndex, and AutoGen.

- Strong understanding of RAG architectures, embeddings, vector databases, semantic search, and retrieval optimization.

- Experience with prompt engineering, tool calling, multi-agent orchestration, and Model Context Protocol (MCP).

- Familiarity with LLM evaluation and observability tools such as LangSmith, Arize, PromptLayer, and Weights & Biases.

- Experience with REST APIs, gRPC, microservices, Docker, Kubernetes, and Terraform.

- Knowledge of cloud platforms such as AWS, Azure, or GCP, along with AI security, performance optimization, and production deployment practices.