Agentic AI Developer

Vibehackers; Dadri, Hyderabad; On-site; INR 1,800,000 - 2,800,000; Full time

Job summary

Vibehackers is seeking an Agentic AI Developer to design, build, and ship AI agents and orchestration flows for production systems. You will focus on turning capabilities into reliable, observable, evaluable agents and integrating them into full-stack applications.

The role emphasizes reliability, observability, memory, governance, and cross-team integration, with a strong focus on cost, latency, and quality across provider ecosystems.

Qualifications

• 3+ years building and shipping production software with hands-on experience building AI agents or LLM-powered applications.
• Hands-on experience with at least one agent framework/SDK and one orchestration framework (LangChain/LangGraph or equivalent).
• Solid understanding of prompting, function/tool calling, structured outputs, context-window management, RAG, embeddings, and vector databases.
• Full-stack fluency: REST/async APIs, relational databases (PostgreSQL), and front-end experience (React).
• Familiarity with cloud providers (AWS/Azure/GCP), containers (Docker), and CI/CD.

Responsibilities

• Design, build, and ship AI agents using modern agent frameworks and orchestration tools.
• Architect multi-agent orchestration and stateful workflows with planning, routing, hand-offs, retries and durable execution.
• Implement tool/function calling, structured outputs, and external integrations.
• Build retrieval and memory layers: RAG pipelines, embeddings, and vector search.
• Establish governance and safety: guardrails, human-in-the-loop, audit trails, and safe-failure behavior.
• Set up evaluation/observability: tracing, telemetry, and LLM-as-judge approaches to improve reliability.
• Integrate agents into APIs, services, and front-end surfaces with platform/product teams.
• Optimize cost, latency, and quality across providers and deployment targets.

Skills

LLM engineering

Agent development

System architecture

Full-stack development

API design

Observability and monitoring

Evaluation and testing

Governance and compliance

Cloud & DevOps

Debugging

Product mindset

Collaboration

Job description

Explicitly focused on building agentic LLM systems and orchestration—heavy on agent frameworks, rapid prototyping, and AI dev tooling.

About the Role

Build and ship production AI agents and orchestration flows that power reasoning, tool use, multi-agent coordination, memory, and governance. Own agent design through production, focusing on reliability, observability, and integration across full-stack applications.

Job Description

Role

Agentic AI Developer responsible for designing, building, and shipping AI agents and orchestration flows for production systems. The role focuses on turning capabilities into reliable, observable, evaluable agents and integrating them into full-stack applications.

Key Responsibilities

• Design, build, and ship AI agents using modern agent frameworks (e.g., OpenAI Agents SDK, Google ADK, Microsoft Agent Framework, AutoGen, CrewAI).
• Architect multi-agent orchestration and stateful workflows with frameworks like LangGraph and LangChain (planning, routing, hand-offs, retries, durable long-running execution).
• Implement tool/function calling, structured outputs, and integrations with external systems (including MCP servers and connectors).
• Build retrieval and memory layers: RAG pipelines, embeddings, vector search, and short- and long-term agent memory.
• Integrate governance and safety: guardrails, policy enforcement, human-in-the-loop checkpoints, audit trails, and safe-failure behavior.
• Establish evaluation and observability: agent evals, LLM-as-judge approaches, tracing, and telemetry (e.g., LangSmith, Langfuse, OpenTelemetry) to measure and improve reliability.
• Integrate agents into APIs, services, and front-end surfaces in collaboration with platform, product, and design teams.
• Optimize for cost, latency, and quality across model providers and deployment targets.

Requirements

• 3+ years building and shipping production software with recent hands-on experience building AI agents or LLM-powered applications.
• Hands-on experience with at least one agent framework/SDK (OpenAI Agents SDK, Google ADK, AutoGen, CrewAI, or similar) and one orchestration framework (LangChain, LangGraph, or equivalent).
• Solid understanding of LLM building blocks: prompting, function/tool calling, structured outputs, context-window management, RAG, embeddings, and vector databases.
• Full-stack fluency: REST / async APIs (FastAPI, NestJS, or similar), relational databases (PostgreSQL), and front-end experience (React).
• Familiarity with cloud providers (AWS, Azure, or GCP), containers (Docker), and CI/CD.
• Strong debugging instincts, product mindset, and judgment for making non-deterministic systems behave reliably.

Nice to Have

• Experience with agent evaluation and LLM observability tooling (LangSmith, Langfuse, Arize).
• Experience with MCP, Temporal or other durable-execution engines, and event-driven architectures.
• Exposure to enterprise/regulatory environments (SSO, RBAC, data governance, compliance).
• Experience with fine-tuning, prompt optimization, or model routing, and open-source contributions in the agent/LLM ecosystem.

Skills

LLM engineering Agent development System architecture Full-stack development API design Observability and monitoring Evaluation and testing Governance and compliance Cloud & DevOps Debugging Product mindset Collaboration