Role: Agentic AI Engineer

Location: Remote

Job Type: Contract

Job Description:

Responsibilities:

• Designs, develops, deploys, and maintains AI-powered applications using Python/FastAPI backends, React/TypeScript frontends, and Google Cloud Vertex AI, while adhering to development best practices and quality standards.
• Takes full end-to-end ownership of assigned GenAI systems, including architectural decisions, feature delivery, operational readiness, production support, and cost optimization.
• Leads by example in adopting AI-augmented development workflows, demonstrating effective collaboration with AI coding assistants (Claude Code, GitHub Copilot) to accelerate delivery and improve code quality.
• Works closely with solution engineers, architects, and product teams to develop technical design specifications and validate that proposed solutions align with architectural standards, non-functional requirements, and business needs.
• Implements LLM orchestration patterns including prompt engineering, retrieval-augmented generation (RAG), multi-agent workflows, and structured output generation.
• Builds and maintains observability pipelines for AI systems platforms, including trace analysis, token usage tracking, cost monitoring, and quality metrics.
• Provides technical guidance and mentorship across the team, upskilling members on agentic development practices, prompt engineering techniques, and AI tool integration.
• Performs cross-platform analysis and trade-off assessments across backend (Python/FastAPI), frontend (React/TypeScript), and AI services (GCP Vertex AI, LangFuse) to ensure consistency and identify optimization opportunities.
• Responsible for troubleshooting and issue analysis, as well as coding, testing, and implementing software enhancements across the full stack.
• Ensures timely delivery of AI initiatives, proactively communicating risks, blockers, and schedule impacts, and driving resolution to maintain delivery commitments.
• Demonstrates exceptional prioritization and multitasking skills to manage concurrent deliverables across services and platforms, handle operational requests, and resolve production issues effectively.
• Uses observability and monitoring tools (e.g., LangFuse, Grafana, Dynatrace, Splunk) to actively review dashboards, investigate anomalies, monitor AI model performance, and track cost metrics.
• Available to support/unblock planned deployments during off hours as needed.

Skills Required:

• AI Coding Assistants (e.g., Claude Code, GitHub Copilot, Cursor, Windsurf)
• Generative AI Application Development/Generative AI Design Patterns
• GenAI cloud platforms (Google Cloud Vertex AI, Gemini, Anthropic Claude, OpenAI)
• LLM Observability and Tracing (LangFuse, LangSmith, or similar)
• Prompt Engineering techniques (e.g., chain-of-thought, few-shot learning, structured outputs)
• Python, FastAPI, async programming, Pydantic, SQLAlchemy ORM
• React, TypeScript, Zustand state management, Material-UI (MUI)
• Data visualization libraries (Recharts, D3.js)
• MySQL/PostgreSQL databases, query optimization, Alembic migrations
• Git, CI/CD, GitHub Actions, ArgoCD
• Docker and docker-compose
• Google Cloud Platform (Vertex AI, Cloud Run, BigQuery, Cloud Storage, IAM)
• Authentication and Authorization (OAuth 2.0, Okta, JWT, RBAC)
• Kubernetes and container orchestration
• Grafana, Prometheus Monitoring
• Dynatrace + Splunk working knowledge to setup and monitor service alerts
• RESTful API Design Patterns, OpenAPI/Swagger Documentation
• Experience with markup languages such as JSON and YAML
• UV package manager, Poetry, modern Python tooling