AI Engineer - Agentic Systems

We are hiring an AI Engineer to design, build, and operate agentic AI systems - LLM-powered agents that reason over enterprise data, call tools, and execute multi-step workflows end to end. This is a hands-on engineering role at the center of how we automate complex technical and operational work. You will take ambiguous problems, decompose them into agent workflows, and ship production services that engineering teams depend on daily. This is an ideal role for an engineer with a strong Python and ML foundation who has already shipped LLM or RAG applications and now wants to go deeper into orchestration, tool-calling, and autonomous multi-agent architectures. You will work within an established platform and architecture, with senior engineers available for design review - but you will own your components from prototype through production., Agent Design & Orchestration

• Build and ship LLM-powered agents that plan, call tools, and complete multi-step tasks using frameworks such as LangChain, LangGraph, or equivalent orchestration libraries.
• Implement multi-agent workflows - planner, executor, reviewer, and specialist roles - including state handling, hand-off logic, retries, and graceful failure paths.
• Design and expose tools to agents via function-calling and Model Context Protocol (MCP) servers, wrapping internal APIs, databases, and enterprise systems as safe, well-scoped agent capabilities.

Retrieval & Knowledge Systems

• Build and operationalize Retrieval-Augmented Generation (RAG) pipelines: chunking, embedding, vector and hybrid search, re-ranking, and context assembly.
• Integrate structured, semi-structured, and unstructured sources - SharePoint, Confluence, Jira, REST APIs, Excel, and SQL warehouses - into retrieval and agent context layers.
• Continuously improve answer grounding and reduce hallucination through better retrieval, prompt design, and context management.

Engineering & Deployment

• Develop production Python services and APIs for agent and model inference using FastAPI, containerized with Docker and deployed through standard CI/CD pipelines.
• Instrument agents with tracing, token and cost accounting, latency monitoring, and structured logging so that behavior is observable and debuggable in production.
• Apply MLOps and LLMOps practices including version control for prompts and configs, automated regression testing, and safe rollout of model or prompt changes.

Evaluation & Quality

• Build evaluation harnesses for agent workflows - golden datasets, task-level success metrics, LLM-as-judge scoring, and regression suites that gate releases.
• Measure and tune for accuracy, latency, and cost, and make explicit trade-offs between them based on the use case.

Collaboration

• Partner with domain experts, data engineers, and product stakeholders to turn manual workflows into reliable automated agents.
• Deliver results through interfaces users actually adopt - Streamlit apps, chat interfaces, dashboards, and embedded integrations.
• Write clear design notes and runbooks, and participate actively in code and design reviews.

• 3-5 years of professional software, ML, or data engineering experience, including at least 1 year building LLM-based or GenAI applications.
• Strong Python engineering skills - not just notebooks. Production code, testing, packaging, async patterns, and API development with FastAPI or similar.
• Hands-on experience with at least one LLM orchestration framework (LangChain, LangGraph, LlamaIndex, Semantic Kernel, or an equivalent) in a shipped application.
• Demonstrated experience building RAG systems: embeddings, vector stores (e.g., FAISS, pgvector, Pinecone, Chroma), and retrieval quality tuning.
• Practical command of prompt engineering, structured output, function/tool calling, and context-window management.
• Working knowledge of SQL and cloud data platforms (Snowflake, Databricks, or equivalent), and comfort writing queries against enterprise schemas.
• Experience containerizing and deploying services with Docker and shipping through CI/CD on a major cloud (Azure, AWS, or Google Cloud Platform).
• Solid grounding in ML fundamentals and familiarity with PyTorch, TensorFlow, or HuggingFace Transformers.
• Clear written and verbal communication, and the judgment to escalate when a problem is under-specified rather than guessing., * Experience building or consuming Model Context Protocol (MCP) servers, or comparable agent tool-integration layers.
• Production experience with multi-agent or agentic workflow systems, including human-in-the-loop checkpoints and approval gates.
• Familiarity with LLM observability and evaluation tooling such as LangSmith, Langfuse, Weights & Biases, or MLflow.
• Experience with workflow orchestration tools - Airflow, Dagster, Prefect - or analytics engineering with DBT.
• Exposure to model fine-tuning or parameter-efficient adaptation (LoRA/PEFT) and knowing when it is - and is not - the right answer.
• Background in a technical engineering domain (semiconductor, hardware validation, manufacturing, or similar) where agents operate over specialized data.
• Experience with AI governance, responsible-AI review, or enterprise security requirements for LLM deployments.