Sr. AI Platform and Orchestration Engineer, Sangli

Job Summary OpenGov is seeking a highly experienced Sr. AI Platform Engineer to serve as both a technical leader and strategic mentor within our growing Pune AI engineering team. You will own the design and production delivery of OpenGov’s internal agentic orchestration and AI delivery infrastructure, including RAG pipelines, agentic workflows, and Snowflake-native AI data products. You will set the engineering standards, technical culture, and decision-making bar that this team builds upon from day one.This role sits at the intersection of platform engineering, applied AI, and cross-functional collaboration. You will work directly with OpenGov’s Data and R&D/Engineering teams to ensure our AI systems are grounded in production-quality, well-governed data. You will be the technical bridge that translates AI experimentation into durable, enterprise-grade systems, and the mentor who ensures those around you can do the same. We are looking for someone with the depth to make hard architectural calls, the communication skills to align cross-functional partners, and the generosity to raise the floor of the entire team, not just their own ceiling. This is not a research role and not a lone-expert role. It is a force-multiplier role.Core Responsibilities - Design and implement production-grade AI orchestration pipelines: RAG systems, agentic workflows, embedding pipelines, and LLM API integrations using Snowflake Cortex, LangGraph, or equivalent frameworks. - Serve as the primary technical mentor for AI engineers through structured code reviews, architectural walkthroughs, and hands-on pair programming, deliberately building team capability over time, not just solving problems yourself.- Partner with OpenGov's Data and R&D/Engineering teams to ensure AI systems are grounded in well-structured, production-quality data: this includes hands-on dbt modeling, alignment on data ownership boundaries, and cost-effective integration of structured and unstructured data into AI workflows. - Coordinate with DevOps and infrastructure teams on AI deployment dependencies: own the requirements definition, drive delivery accountability, and ensure AI platform work is not blocked by unclear handoffs.- Establish and enforce engineering standards for the AI team: testing and evaluation practices, deployment patterns, prompt versioning, observability frameworks, and core system design principles. - Translate ambiguous or early-stage product requirements into pragmatic, iterative engineering plans with clear scope, sequencing, and success criteria the team can execute against with confidence.- Implement monitoring, evaluation, and feedback mechanisms to track agent reliability across the organization. - Continuously evaluate and introduce emerging AI tools and frameworks, with discipline, to enhance OpenGov’s platform capabilities without creating unnecessary complexity. - Contribute to architectural standards for Model Context Protocol (MCP), agent governance, and data security across AI systems.- Operate with meaningful technical autonomy: own engineering decisions within established architectural guardrails, apply sound judgment in the absence of real-time US team availability, and escalate appropriately when decisions carry outsized risk or require broader alignment. Required Experience- Bachelor’s degree in Computer Science, Engineering, or a related field. - 7–10 years of experience in software engineering, data engineering, or applied AI engineering, with at least 2 years building and owning production AIsystems, with direct hands-on experience in agentic workflows, RAG pipelines, and/or LLM-integrated applications.- Hands-on dbt experience: you have written and maintained dbt models, understand transformation logic, and can work with a data team as a peer, not just a consumer of their outputs. - Strong Snowflake expertise including AISQL functions, semantic modeling, and query optimization. - Proficiency with AI and LLM frameworks: LangChain, LangGraph, or equivalent; RAG architecture design; integration of commercial LLM APIs (OpenAI, Anthropic, Gemini, or similar).- Solid Python and SQL fundamentals with a proven ability to productionalize AI systems. - Demonstrated experience establishing engineering standards and technical culture on a team, not just executing as an individual contributor. - Strong cross-functional communication skills: can align Data, R&D, and product stakeholders without hoarding context or creating silos. - AI-native by practice: actively building with LLMs and agentic coding tools today. Can explain RAG, agent orchestration, and evaluation with concrete examples from production work. Nice to Have - Experience with Airia, CrewAI, or similar multi-agent orchestration frameworks beyond LangChain.- Familiarity with Snowpark Container Services (SPCS). - Exposure to event-driven architectures and workflow orchestration engines. - Experience with CI/CD via GitHub in data engineering or AI pipeline contexts. - Prior experience at an AI-native startup or fast-moving AI product team. - Experience collaborating across timezones with async-first communication norms