New: upload your resume and get matched to AI jobs. Free to start →

Sr AI Engineer, Agentic Systems

Bengaluru, India • Full-time

Posted 24d ago

Job Location

Bengaluru, India

Tech Stack

Remote Work Policy

On-site

Employment Type

Full-time

Categories

AI Agent Engineer

About the job

We are seeking senior engineers to join our Enterprise AI Incubation team, focused on building intelligent applications that learn from data and actively assist in running the business. In this role, you will redesign existing workflows by implementing end-to-end agent systems that drive significant enterprise transformation. You will own the entire lifecycle of your agent systems, from understanding business needs and designing architectures to coding, deploying, and maintaining them in production. This involves engineering robust infrastructure around model endpoints, integrating custom tooling, context pipelines, automated evaluations, and guardrails to ensure resilience against real-world data complexities. You will also exercise critical judgment in determining the appropriate solution for a problem, whether it's an agent, simpler automation, or no solution at all, with the authority to adjust or halt work that lacks impact. We encourage a collaborative, low-ego approach, leveraging AI coding tools as integral partners in the engineering process.

Responsibilities

  • Lead product discovery with Product Managers and domain experts to understand workflows, define problems, and establish success criteria for agentic solutions.
  • Design, build, test, and deploy production agents, automations, and internal tools using coding agents, LLM APIs, and agent frameworks, integrated with internal platforms and business systems.
  • Transform complex processes into multi-agent workflows for tasks such as deal qualification, order fulfillment, customer health monitoring, and HR/IT coordination.
  • Engineer agents for autonomy and reliability, including tool and orchestration flows, context management, caching, retries, and failure handling.
  • Leverage full-stack engineering across backend services, APIs, data models, and user interfaces to deliver high-ownership, user-facing agent systems.
  • Apply solid software engineering practices to AI systems, treating prompts, skills, configs, and specs as versioned artifacts with code review, tests, CI/CD, and staged rollouts.
  • Implement evaluation, guardrails, and quality control, deriving evals from workflow data, establishing quality gates, integrating human-in-the-loop approvals, and monitoring production runs.
  • Use measured results to evolve or retire agents and create reusable patterns and libraries from successful systems.

Requirements

  • Approximately 7+ years of professional software engineering experience in production systems.
  • Approximately 2+ years of hands-on experience building AI agents and agent-powered production applications with measurable outcomes.
  • Strong full-stack engineering background with a track record of designing, building, and owning services end-to-end, including backend APIs, integrations, data models, and user interfaces.
  • Builder mindset: comfortable defining baselines and metrics, reporting results in business terms, working in fast-paced environments, and iterating on solutions.
  • Proficiency in system design, including breaking down complex problems, designing APIs and data models, and reasoning about performance and failure modes.
  • Experience with algorithms, data structures, access control, and data provenance.
  • Familiarity with spec-driven development and execution discipline using version control, code review, automated tests, CI/CD, staged rollouts, logging, metrics, and tracing.
  • Experience building agents in code using LLM APIs, SDKs, and libraries.
  • Experience designing robust agent harnesses and multi-agent orchestrations, managing context and state, and ensuring reliability.
  • Experience establishing continuous evaluation and safety mechanisms, including turning production failures into test cases and enforcing guardrails.
  • Clear judgment on AI fit, making tradeoffs around model choice, latency, cost, context strategy, and autonomy.
  • Knowledge of knowledge/context graphs, GraphRAG, and hybrid retrieval is preferred.
  • Experience with agent frameworks and runtimes like Google ADK, LangGraph, or OpenAI style is preferred.