Senior Agentic Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop, deploy, and manage elements of Brahma’s internal agentic architecture.

• Create gateway and routing functionalities, which include provider fallbacks, budget enforcement, usage attribution, and access policies.

• Construct and manage MCP servers and connectors for Git, CI/CD, work tracking, and documentation.

• Take ownership of CI/CD processes, containers, and infrastructure-as-code for agentic AI services.

• Implement governed agent workflows that feature structured inputs and outputs, human approval gates, and multi-agent patterns.

• Develop and maintain memory and context services, including session and long-term memory, context compaction, retrieval, and progressive tool disclosure.

• Manage production operations encompassing monitoring, alerting, rollbacks, cost management, incident response, upgrades, and patches.

• Write unit tests, integration tests, and regression evaluations for agents, tools, and routing in CI.

• Oversee tracing and usage-reporting pipelines across model, tool, and agent calls.

• Construct components in compliance with security standards and address identified security issues.

• Maintain services and open-source dependencies, diagnose failures to their root cause, and engage in incident response and future on-call rotations.

• Create and sustain developer surfaces, including CLI, chat integrations, coding-agent harness configurations, and shared agent and skills catalogs.

• Assist teams in adopting coding agents through documentation, examples, and collaboration.

• Document solutions and share patterns and lessons through demonstrations, guides, and collaborative efforts.

• Contribute to design reviews and architecture decision records, evaluate emerging agent frameworks, and strengthen effective patterns for enterprise-scale applications.

⛳️ Requirements

• 5+ years of experience in software engineering.

• Expertise in server-side Python development.

• Practical experience in delivering production features built on LLM APIs and tool calling, including understanding failure modes and cost considerations.

• Experience in building MCP servers or equivalent tool connectors, rather than solely consuming them.

• Proven track record in developing reliable APIs, services, and asynchronous or event-driven systems.

• Experience with automated testing, CI, logging, metrics, tracing, and debugging production issues.

• Knowledge of OAuth 2.0, OIDC, secrets management, least privilege principles, and LLM-specific risks such as prompt injection.

• Documented history of supporting colleagues and teams in adopting new technologies.

• Regular use of AI coding tools such as Claude Code, Cursor, or Copilot while maintaining code quality, test coverage, and review standards.

• Familiarity with A2A, agent frameworks like LangGraph or Google ADK, or durable workflow engines such as Temporal or Prefect.

• Experience with agent memory designs, vector databases like pgvector or Qdrant, or hybrid search solutions.

• Experience in configuring coding agents for teams, including skills, subagents, hooks, and sandboxing.

• Experience running a multi-model gateway or routing layer in production is advantageous.

• Familiarity with LLM evaluation tools, LLM-judged regression tests, and OpenTelemetry is a plus.

• Proven record of transitioning emerging agent tools or patterns from evaluation into production is a bonus.

• Experience with services on GCP, AWS, or Azure, utilizing Docker, Kubernetes, and Terraform or similar infrastructure-as-code tools is a plus.

🏝️ Benefits

• Flexible remote work arrangement with hours overlapping UTC+0 to UTC+3.

• Opportunity to engage with state-of-the-art generative AI models and enterprise media technology.

• Be part of a dedicated, high-caliber agentic AI unit.

• Collaborate with teams in Architect, Product Management, ML Engineering, Security Engineering, and Infrastructure & DevOps.

• Gain exposure to open protocols, open-source components, and proprietary services.

• Opportunity to create and deploy production agentic AI systems.

• Participate in knowledge sharing through demos, guides, documentation, and collaborative efforts.