We are seeking an accomplished, hands-on Senior Software Engineer to lead the design and implementation of core artificial intelligence capabilities within our Intelligent Data Analytics Platform, with a particular emphasis on multi-agent orchestration and semantic search. This position is intended for a highly capable individual contributor who is able to operate effectively at both architectural and implementation levels — an engineer who anchors the team technically by producing production-grade code, resolving the most demanding problems, and establishing engineering standards by example.

The successful candidate will serve as a principal contributor to an AI-first platform that enables users to explore, query, and analyze enterprise BigQuery data through agentic tools and capabilities.

1. Architecture and System Design

Contribute to the design of scalable, multi-agent AI architectures.

Design components and modules across agent orchestration, tool systems, and large language model (LLM) integration.

Evaluate trade-offs across architectural choices (e.g., single- versus multi-agent designs, retrieval-augmented generation versus fine-tuning, deterministic versus probabilistic pipelines).

Participate in design reviews and contribute to Architecture Decision Records (ADRs).

2. Hands-On Engineering and Execution

Produce production-grade code across agent frameworks, backend APIs, and frontend interfaces on a daily basis.

Develop and evolve reusable AI components, including agent tools, embedding pipelines, and evaluation frameworks.

Implement LLM-powered workflows, including natural-language-to-SQL generation, semantic search, and metadata enrichment.

Develop services that enable intelligent data access, such as vector search, hybrid retrieval, and query scope management.

Implement guardrails, validation layers, and observability mechanisms for AI-generated outputs.

3. Full-Stack Development

Build performant backend services (Python/ FastAPI) and interactive frontend applications (Angular/React) for data exploration.

Develop both conversational (chat) and structured (API) interfaces for analytical workloads.

Construct evaluation and benchmarking tooling to support continuous measurement of AI quality.

Assume end-to-end ownership of features, from initial design through deployment and ongoing monitoring.

4. Semantic Search and Embeddings

Implement vector embedding pipelines for metadata discovery using pgvector.

Develop semantic retrieval capabilities across datasets, tables, and columns, employing hybrid search strategies.

Optimize search relevance through embedding strategies, re-ranking, and rigorous evaluation metrics.

Contribute to the platform's data quality and governance capabilities.

5. Engineering Excellence

Produce clean, maintainable, and scalable code that adheres to industry best practices.

Participate actively in code reviews and establish quality standards through exemplary personal contributions.

Conduct root-cause analysis on agent failures and implement systematic remediations.

Serve as the team's technical anchor and primary point of reference for complex implementation challenges.

6. Collaboration

Partner with Product, Data Engineering, and Platform teams to ensure successful feature delivery.

Support colleagues through pair programming, knowledge sharing, and technical mentorship.

Contribute to sprint planning, effort estimation, and technical feasibility assessments.

Assist in onboarding new team members and disseminating domain expertise across the organization.

Required Qualifications

Bachelor’s degree in Computer Science, Engineering, Data Science, or a related technical field.

8 + years of professional software engineering experience with demonstrated hands-on coding proficiency.

Demonstrable experience building AI-powered applications or operating LLM-based systems in production environments.

Proven ability to interpret ambiguous requirements and independently deliver functional, well-tested software.

Strong debugging and problem-solving capabilities across the full technology stack.

A demonstrated record of owning and delivering complex features from inception through completion.

Technology Stack

Programming Languages and Frameworks: Python (primary), Java, JavaScript/TypeScript, Angular/React

Artificial Intelligence and Machine Learning: Google ADK, LangChain/LangGraph, OpenAI and Gemini APIs, prompt engineering, retrieval augmented generation (RAG) pipelines

Data and Cloud Infrastructure: Google Cloud Platform (BigQuery, Vertex AI, and Cloud Run preferred)

Backend Technologies: FastAPI, Pydantic, SQLModel/SQLAlchemy, PostgreSQL with pgvector

Frontend Technologies: Angular or React, TypeScript

Continuous Integration, Continuous Delivery, and Infrastructure: Terraform, GitHub Actions, Docker Evaluation: Custom evaluation frameworks, LLM-as-judge methodologies

Preferred Qualifications

Experience with the Google Agent Development Kit (ADK) or comparable agent frameworks, such as  CrewAI, or LangGraph.

Applied machine learning experience encompassing embeddings, classification, clustering, natural language processing, and evaluation metrics.

Demonstrated experience with vector databases and semantic retrieval optimization.

Familiarity with data engineering practices and data governance processes.

Prior experience developing internal developer tooling or platform SDKs.