Description
Were looking for a Lead AI Engineer with minimum 10 years of experience who thrives on building production-grade, agentic AI systems that power real business workflows. You have strong Python skills, hands-on experience working with LLMs in production (prompt engineering, tool/function calling, structured outputs and RAG), and working knowledge of LangChain or LangGraph (or a comparable framework such as LlamaIndex, CrewAI or Semantic Kernel).
You are comfortable writing solid SQL, working with at least one major cloud, and shipping reliable services using Git, Docker and a modern API framework like FastAPI.
As a Lead AI Engineer on the Tech Hub team, you will play a key role in building on that platform shipping agent harnesses, writing the tools those agents call, and owning the reliability and evaluation of what goes to production.
This is not a research role : you will prototype, ship, monitor and iterate on features used by real teams, working closely with our U.S. AI & Innovation team and cross-functional partners across Engineering, Data, QA and Product.
How You Will Make An Impact
- Design and build agent harnesses in Python using LangChain and LangGraph, including tool-calling, structured outputs (Pydantic / JSON schema), retries, streaming and memory
- Package agents as Dataiku Code Agents, custom plugins, and Python / SQL recipes that fit cleanly into production flows and scenarios
- Write the tools agents use API integrations, SQL queries against Snowflake, and Knowledge Bank retrievals with clear contracts and Pydantic validation
- Build evaluation harnesses (golden datasets, LLM-as-judge, regression suites) using Dataiku Evaluations, and wire them into CI
- Implement guardrails around tool execution : auth scoping, input / output validation, PII and prompt-injection protections, and hallucination mitigation
- Own what you ship prototype, deploy through Dataiku, monitor traces, and fix issues quickly when something breaks in production
- Partner with data engineers on Snowflake-backed retrieval patterns (Cortex Analyst and Cortex Search Services) and with platform teams on observability, security and cost
- Help shape internal patterns and AI engineering standards as the stack evolves, contributing to design reviews and sharing knowledge across the India and U.S. teams
- Participate in a collaborative DevOps environment, working closely with developers, QA, DBAs and product partners across your first 90 days :
By the end of your first 90 days, you will have shipped at least one production agent end-to-end such as a retrieval-backed analyst assistant or a workflow automation harness. You will have traces and evaluations running against a golden dataset, a Dataiku plugin or Code Agent registered in the LLM Mesh, and a clear opinion about what our next agent should do.
What You Need To Be Successful
- 3+ years of professional Python experience, with production experience building and operating services
- 1+ years of hands-on work with LLMs in production : prompt engineering, tool / function calling, structured outputs and RAG
- Working knowledge of LangChain or LangGraph or a comparable framework like LlamaIndex, CrewAI or Semantic Kernel
- Solid SQL skills and comfort with at least one cloud platform (AWS, Azure or GCP)
- Fluency with Git, Docker and a modern API framework like FastAPI
- Solid understanding of data security and responsible AI practices, particularly in PCI-compliant or regulated environments
- Proven ability to work independently and within a team, managing priorities across concurrent projects and time zones
- Strong written and verbal communication skills; able to work effectively with both technical and non-technical stakeholders
- A bachelors degree is not required equivalent practical experience (including bootcamps, self-taught work, career changes or non-CS technical degrees) counts
Bonus Skills
- Hands-on experience with Dataiku DSS as a coder : Python / SQL recipes, scenarios, managed folders, code environments, the dataiku and dataikuapi clients, webapps or plugin development
- Experience with Dataiku LLM Mesh, Knowledge Banks, Prompt Studio, or Visual / Code Agents
- Experience with Snowflake, Snowpark, or Snowflake Cortex (Search, Analyst, Agents)
- Experience with LLM observability tools : LangSmith, Langfuse, MLflow or OpenTelemetry
- Experience designing evaluation frameworks (RAGAS, DeepEval, LLM-as-judge, multi-turn regression)
- Familiarity with multi-agent patterns : supervisor / router, subagent / handoff, reflection, human-in-the-loop
- A Dataiku Developer or Advanced Designer certification
- Experience in loyalty, martech, adtech or a comparable data-rich B2B domain
(ref:hirist.tech)
