Manager - Senior AI/ML Engineer

Role Overview We are seeking a Senior AI/ML Engineer with 5–9 years of experience designing, building, and operating production-grade AI and Generative AI solutions. You will provide hands-on technical leadership across solution architecture, data and model pipelines, agentic systems, evaluation, cloud deployment, and observability. The ideal candidate pairs deep AI/ML expertise with strong software-engineering discipline and sound architectural judgment and can lead delivery for complex enterprise use cases. What You Will Do Own AI/ML and GenAI solutions end to end — data pipelines, model and prompt workflows, APIs, evaluation, deployment, observability, and continuous optimization. Design enterprise RAG platforms: secure ingestion, chunking, embeddings, hybrid/vector search, reranking, citations, and access-aware retrieval. Build production agentic systems using tool/function calling, structured outputs, planning and memory, multi-agent orchestration, human-in-the-loop approvals, failure recovery, and auditable traces. Architect and operate MCP clients and servers that expose enterprise tools, resources, and prompts — with secure transports (stdio, Streamable HTTP), authentication, least-privilege access, tenant isolation, and protection against prompt injection and unsafe tool execution. Integrate agents with enterprise systems (document repositories, source control, ticketing, databases, ERP/CRM, cloud services) through reusable connectors and governance patterns. Define evaluation strategies and quality gates for accuracy, groundedness, safety, latency, and cost, and establish end-to-end observability for agent and MCP activity. Build production services in Python with strong engineering practices, GitHub-based CI/CD, and cloud-native deployment on AWS or Azure using Docker, Kubernetes, and infrastructure as code. Partner with product, architecture, data science, security, and business stakeholders; lead design and architecture reviews and mentor engineers. Required Qualifications Bachelor's or Master's in Computer Science, Data Science, AI/ML, Engineering, or a related field — or equivalent practical experience. 5–9 years developing production software, data, ML, or AI solutions, including hands-on delivery of GenAI/LLM applications. Advanced Python and practical experience with data/ML libraries (pandas, NumPy, scikit-learn, PyTorch, TensorFlow, or equivalent). Strong grasp of LLM and agentic architecture: prompting, context engineering, embeddings, RAG, tool/function calling, structured outputs, orchestration, evaluation, and human-in-the-loop controls. Proven experience designing APIs, distributed services, and event-driven or asynchronous workflows with secure tool execution for AI agents. Hands-on experience with Git/GitHub and CI/CD, including automated build, test, security-scan, and deployment workflows. Strong experience with AWS or Azure and containerized deployment using Docker; Kubernetes and infrastructure-as-code experience expected. A current, role-relevant AWS AI/ML certification or Microsoft Azure AI certification is mandatory. Hands-on production experience with Model Context Protocol (MCP) is mandatory — consuming and developing MCP servers, integrating clients with agent frameworks, defining tools/resources/prompts, managing stdio or Streamable HTTP transports, and implementing security, approvals, testing, and tracing. MLOps/LLMOps practices: experiment tracking, model and prompt versioning, tracing, evaluation, monitoring, and cost optimization. Preferred Experience GenAI or agent frameworks such as OpenAI Agents SDK, LangGraph/LangChain, Semantic Kernel, AutoGen, LlamaIndex, Amazon Bedrock Agents, or Azure AI Foundry Agent Service. Enterprise search and vector technologies (pgvector, Pinecone, Weaviate, Milvus, Elasticsearch/OpenSearch, Azure AI Search, Amazon OpenSearch, or equivalent). LLMOps/observability platforms (MLflow or comparable) for tracing, evaluation, prompt management, and governance