Senior AI Engineer

We are seeking a highly skilled AI Senior Engineer to design, develop, and scale production-grade agentic AI systems. In this role, you will architect autonomous and multi-agent solutions that leverage reasoning, tool usage, and seamless integration with enterprise systems to automate complex workflows from start to finish. This position offers the opportunity to work on cutting-edge AI technologies and deliver impactful solutions for enterprise clients.

Key Responsibilities:
Build agents: Design and deploy LLM-powered agents and multi-agent systems that incorporate planning, memory, and tool utilization.
Orchestration: Develop and implement workflows using frameworks such as LangGraph, CrewAI, AutoGen, or Semantic Kernel.
Integration: Connect agents to enterprise APIs, databases, and applications through function calling and multi-channel processing (MCP).
Retrieval: Construct robust retrieval-augmented generation (RAG) pipelines using vector databases, chunking techniques, and hybrid search methods.
Quality: Establish evaluation frameworks, guardrails, and observability tools to ensure system reliability, safety, and cost efficiency.
Production: Deploy solutions on cloud platforms such as Azure, AWS, or GCP, utilizing CI/CD pipelines, containerization, and best practices in LLM operations (LLMOps).
Leadership: Mentor engineering team members, conduct code reviews, and define technical standards to drive excellence in AI delivery.

Required Qualifications:
- Minimum of 6 years in software engineering, including at least 2 years of experience building production-grade LLM/Generative AI applications.
- Expert proficiency in Python, with strong skills in API design (FastAPI) and solid software engineering fundamentals.
- Hands-on experience with leading large language models (OpenAI, Anthropic Claude, Gemini, or open-source alternatives) and expertise in prompt and context engineering.
- Demonstrated experience with agent frameworks, retrieval-augmented generation (RAG), and vector stores such as Pinecone, pgvector, or Azure AI Search.
- Proficiency with containerization and orchestration tools like Docker and Kubernetes, along with cloud AI services including Azure OpenAI, AWS Bedrock, and Google Vertex AI.
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related technical field.

Preferred Qualifications and Benefits:
- Experience developing MCP servers or enabling agent-to-agent (A2A) integrations.
- Familiarity with LLM evaluation and tracing tools such as LangSmith, Langfuse, or Arize, and experience with fine-tuning language models.
- Contributions to open-source AI projects or published technical research in relevant areas.

Join us to build production-grade agentic AI solutions for enterprise clients within a collaborative, hands-on team environment. You will have real ownership of your projects, access to modern tooling, and ample opportunities for professional growth.