Senior Agentic Engineer

Brahma

. Build, ship, and operate components of Brahma’s internal agentic setup .

Posted 11/7/2026full-timeRemote • United StatesSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in server-side Python development and building reliable APIs and services, with a strong focus on CI/CD, automated testing, and production operations. Proficient in implementing agent workflows and managing infrastructure-as-code across cloud platforms.

Highest-signal resume keywords

Server-Side Python DevelopmentCI/CD ManagementAutomated TestingAPI DevelopmentAgent Frameworks

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

PythonAPI DevelopmentAutomated TestingInfrastructure-As-CodeEvent-Driven SystemsOAuth 2.0LLM APIsMemory DesignsVector DatabasesDocker

Soft Skills

DocumentationCollaborationMentoring

Tools & Technologies

GitCI/CDKubernetesTerraformGCPAWSAzureOpenTelemetryClaude CodeCursor

Industry Keywords

Agent FrameworksMCP ServersAsynchronous SystemsSecurity StandardsIncident Response

Tech Stack

Tools & technologies

AWSAzureDockerGoogle Cloud PlatformKubernetesPythonTerraform

About the role

Key responsibilities & impact

Build, ship, and operate components of Brahma’s internal agentic setup
Build gateway and routing features including provider fallbacks, budget enforcement, usage attribution, and access policies
Build and operate MCP servers and connectors to Git, CI/CD, work tracking, and documentation
Own CI/CD, containers, and infrastructure-as-code for agentic AI services
Implement governed agent workflows with structured inputs and outputs, human approval gates, and multi-agent patterns
Build and operate memory and context services including session and long-term memory, context compaction, retrieval, and progressive tool disclosure
Own production operations including 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
Own tracing and usage-reporting pipelines across model, tool, and agent calls
Build components according to security standards and fix security findings
Maintain services and open-source dependencies, diagnose failures to root cause, and participate in incident response and future on-call rotation
Build and maintain developer surfaces including CLI, chat integrations, coding-agent harness configuration, and shared agent and skills catalogs
Help teams adopt coding agents through documentation, examples, and pairing
Document solutions and share patterns and lessons through demos, guides, and pairing
Contribute to design reviews and architecture decision records, vet emerging agent frameworks, and harden effective patterns for enterprise scale

Requirements

What you’ll need

5+ years of software engineering experience
Primary expertise in server-side Python development
Hands-on experience shipping production features built on LLM APIs and tool calling, including failure modes and cost considerations
Experience building MCP servers or equivalent tool connectors, not only consuming them
Proven experience building reliable APIs, services, and asynchronous or event-driven systems
Experience with automated testing, CI, logging, metrics, tracing, and debugging production issues
Practical knowledge of OAuth 2.0, OIDC, secrets management, least privilege, and LLM-specific risks such as prompt injection
Track record of documenting work and helping colleagues and teams adopt new technology
Pragmatic daily use of AI coding tools such as Claude Code, Cursor, or Copilot while maintaining code quality, test coverage, and review standards
Experience with A2A, agent frameworks such as LangGraph or Google ADK, or durable workflow engines such as Temporal or Prefect
Experience with agent memory designs, vector databases such as pgvector or Qdrant, or hybrid search
Experience configuring coding agents for teams, including skills, subagents, hooks, and sandboxing
Experience running a multi-model gateway or routing layer in production is nice to have
Experience with LLM evaluation tools, LLM-judged regression tests, and OpenTelemetry is nice to have
Track record of bringing emerging agent tools or patterns from evaluation into production is nice to have
Experience running services on GCP, AWS, or Azure with Docker, Kubernetes, and Terraform or equivalent infrastructure-as-code is nice to have

Benefits

Comp & perks

Remote work arrangement with working hours overlapping UTC+0 to UTC+3
Opportunity to work with cutting-edge generative AI models and enterprise media technology
Dedicated, high-caliber agentic AI unit
Collaboration with Architect, Product Management, ML Engineering, Security Engineering, and Infrastructure & DevOps teams
Exposure to open protocols, open-source components, and proprietary services
Opportunity to build and ship production agentic AI systems
Knowledge sharing through demos, guides, documentation, and pairing