Software Engineering Manager, AgentOps

Jobtailor

Bengaluru

On-site

INR 4,000,000 - 7,000,000

Full time

10 days ago

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Jobtailor is seeking a leader to build and guide a team of AgentOps Forward Deployed Engineers in Bengaluru. You will own performance, growth, and career progression while advancing production-grade AI agent systems.

Join a culture focused on continuous improvement, strong engineering craft, and psychological safety, as you set cadence, remove blockers, and drive high-impact AI use cases from prototype to production.

Qualifications

Has led or mentored engineers and is ready to own hiring, performance, and growth.
Builds LLM-powered systems and AI agents in production while staying hands-on with code.
Strong Python and backend engineering with cloud-native, distributed systems.
Experience with agent orchestration or multi-agent frameworks such as CrewAI, LangGraph, or ADK.
Experience with LLM observability tooling.
Expertise in at least one public cloud: AWS, Azure, or GCP.
Understanding end-to-end agent lifecycle including identity, observability, guardrails, and production operations.
Ability to design with trade-offs among quality, latency, cost.
Excellent communication and stakeholder engagement.
Bachelor's or Master's in CS, AI/ML, or related field, or equivalent experience.
Experience productionizing agentic applications.
Familiarity with MCP, A2A, context engineering, and HITL agent execution.
Familiarity with AI observability and evaluation frameworks such as Langfuse, LangSmith, or Arize Phoenix.
Fluency in AI pair-programming tools such as Cursor or Claude Code.

Responsibilities

Hire, coach, and develop a team of AgentOps Forward Deployed Engineers, owning performance, growth, and career progression
Foster an inclusive, high-performing culture of continuous improvement, engineering craft, and psychological safety
Set goals, run delivery cadence, and remove blockers so the team ships with quality and speed
Lead design reviews and set technical patterns and standards
Take high-impact agentic AI use cases from prototype to production using reusable connectors, shared services, and clean crew hand-offs
Establish standardized practices for agent development, orchestration, and LLMOps
Instrument agent crews with end-to-end observability for traces, cost, tokens, latency, and error rates
Own reliability, performance, and cost targets for production agentic workloads
Establish guardrails, constraints, risk controls, and acceptance criteria for agent-driven work
Own agent and connector identity, authentication, credentials, RBAC, and audit models
Ensure agent crews meet regulatory, security, and data-privacy requirements
Manage intake, prioritization, and cross-team dependencies
Translate business needs into clear acceptance criteria
Partner with product, research, cloud, data science, and engineering leaders across OCTO
Advise senior leadership on agentic AI capabilities, trade-offs, and operational risk
Evaluate emerging agent orchestration, multi-agent framework, and LLMOps tools and patterns
Pilot tools and patterns that improve platform capability, reliability, and developer experience

Skills

Team leadership

Mentoring

Python programming

Cloud-native backend

Agent orchestration

Multi-agent frameworks

LLM observability

Productionizing apps

Education

Bachelor's in CS

Master's in AI/ML

Tools

AWS

Azure

GCP

CrewAI

LangGraph

Langfuse

LangSmith

Arize Phoenix

Cursor

Claude Code

Job description

Hire, coach, and develop a team of AgentOps Forward Deployed Engineers, owning performance, growth, and career progression
Foster an inclusive, high-performing culture of continuous improvement, engineering craft, and psychological safety
Set goals, run delivery cadence, and remove blockers so the team ships with quality and speed
Lead design reviews and set technical patterns and standards
Take high-impact agentic AI use cases from prototype to production using reusable connectors, shared services, and clean crew hand-offs
Establish standardized practices for agent development, orchestration, and LLMOps
Instrument agent crews with end-to-end observability for traces, cost, tokens, latency, and error rates
Own reliability, performance, and cost targets for production agentic workloads
Establish guardrails, constraints, risk controls, and acceptance criteria for agent-driven work
Own agent and connector identity, authentication, credentials, RBAC, and audit models
Ensure agent crews meet regulatory, security, and data-privacy requirements
Manage intake, prioritization, and cross-team dependencies
Translate business needs into clear acceptance criteria
Partner with product, research, cloud, data science, and engineering leaders across OCTO
Advise senior leadership on agentic AI capabilities, trade-offs, and operational risk
Evaluate emerging agent orchestration, multi-agent framework, and LLMOps tools and patterns
Pilot tools and patterns that improve platform capability, reliability, and developer experience

Requirements

Has led, coached, or mentored engineers as a manager, tech lead, or team lead and is ready to own hiring, performance, and growth
Builds LLM-powered systems, AI agents, or workflow automation in production and remains hands-on with code
Strong Python and backend/platform engineering experience with cloud-native, distributed systems
Experience with agent orchestration or multi-agent frameworks such as CrewAI, LangGraph, or ADK
Experience with LLM observability tooling
Expertise in at least one public cloud platform: AWS, Azure, or GCP
Understanding of the end-to-end agent lifecycle, including orchestration, identity/authentication, observability, guardrails, and reliable production operations
Ability to design with trade-off awareness across quality, latency, cost, resilience, and maintainability
Excellent communication and stakeholder-engagement skills
Bachelor's or Master's in Computer Science, AI/ML, or a related field, or equivalent practical experience
Experience productionizing agentic applications
Familiarity with MCP, A2A, context engineering, and HITL agent execution
Familiarity with AI observability and evaluation frameworks such as Langfuse, LangSmith, or Arize Phoenix
Fluency in AI pair-programming tools such as Cursor or Claude Code

Core Competencies

Demonstrates expertise in leading and developing engineering teams while driving the performance and growth of agentic AI systems. Proficient in building LLM-powered applications, ensuring reliability, observability, and compliance within production environments.

Highest-signal resume keywords