Agentic AI Engineer
Location
India
Posted
2 days ago
Salary
0
Seniority
Mid Level
No structured requirement data.
Job Description
Agentic AI Engineer
Oxydata Software
Role Description We are looking for an Agentic AI Engineer to lead the design and implementation of multi-agent AI systems across our product and client delivery portfolio. This role is not about building dashboards — it is about architecting autonomous AI workflows that reason, plan, use tools, and execute multi-step tasks with minimal human intervention. You will work in a small, senior team using AI-assisted development tools as standard practice. What You'll Build - Multi-Agent Orchestration - Design and implement multi-agent pipelines using LangGraph and CrewAI - Agent role definition, task decomposition, inter-agent communication, and state management - Supervisor/worker agent architectures for complex, multi-step reasoning tasks - Workflow Automation - Build production automation workflows using N8N — triggers, conditionals, API calls, data transforms - Integrate AI agents into broader business process automation pipelines - Design human-in-the-loop checkpoints for workflows requiring approval or escalation - Tool Use & Function Calling - Implement tool-calling agents with access to APIs, databases, search, and file systems - Build custom tools and MCP (Model Context Protocol) servers for agent consumption - Memory management — short-term, long-term, and episodic memory for persistent agents - Multimodal AI - GPT Vision integration for document parsing, screenshot analysis, and visual data extraction - Multimodal pipelines combining text, image, and structured data inputs - RAG & Knowledge Retrieval - Integrate RAG pipelines as retrieval tools within agentic workflows - Vector search (pgvector, Pinecone, or similar) for agent knowledge grounding - Prompt engineering for agent personas, reasoning chains, and output formatting - Production Deployment - Deploy agentic systems on self-hosted VPS infrastructure - Observability, logging, and failure handling for long-running agent workflows - API endpoints (FastAPI) exposing agent capabilities to frontend and external systems Qualifications - Bachelor's in Computer Science, Software Engineering, AI, or related field - 1–4 years in AI/ML engineering with hands-on production experience in agentic or LLM-based systems - Demonstrated production experience with LangGraph and/or CrewAI - Hands-on N8N workflow design and deployment - GPT Vision or equivalent for image/document understanding - Python (primary); comfortable reading JavaScript - OpenAI API, Claude API, function calling, tool use, structured outputs - System prompts, chain-of-thought, ReAct patterns, output formatting - Embeddings, vector search, retrieval grounding — as agent tools - FastAPI for exposing agent capabilities as APIs - Git, VPS/cloud deployment, basic Linux administration, error handling for async workflows Nice-to-Haves - LangChain or LlamaIndex for knowledge-base construction - MCP (Model Context Protocol) server development - Experience with AI-assisted development tools (Cursor, GitHub Copilot) - Docker for containerised agent deployment - CI/CD pipelines for agent workflow testing and deployment - React.js — basic frontend ability to build simple agent UIs or dashboards - Experience with structured output validation (Pydantic, instructor library) Benefits - Work on real client deployments — not internal tools or proofs of concept - AI-first development culture — Cursor and Claude are standard tools, not novelties - Small, senior team — high ownership, direct impact, no bureaucracy - Competitive compensation commensurate with experience How to Apply Submit your CV via our careers page: https://oxydata.ai/careers
Related Guides
Related Job Pages
More AI Engineer Jobs
Senior Elastic ML, Gen AI Engineer
KyndrylWe design, build, manage and modernize the mission-critical technology systems that the world depends on every day.
• Design, build, and scale machine learning and generative AI solutions on the Elastic Stack • own the ML and Gen AI capabilities end-to-end—from anomaly detection and semantic search to vector-powered RAG • Design and implement Elastic ML solutions: anomaly detection, data frame analytics, and forecasting • Build semantic and hybrid search using vector search, dense/sparse vectors, and ELSER • Develop Gen AI / RAG pipelines using Elasticsearch as a vector store • Deploy and manage NLP and transformer models in Elasticsearch via Eland • Design data models, mappings, and ingestion flows optimized for vector and ML workloads • Tune relevance, embeddings, and retrieval quality; evaluate and improve search/RAG performance • Build Kibana dashboards and ML jobs for monitoring, alerting, and explainability • Partner with data, platform, and product teams to operationalize ML/Gen AI features at scale
• Manage and evolve the end-to-end architectural blueprint for cloud-native applications at scale — covering compute, data, networking, security, and observability layers on AWS. • Define and promote agentic AI architecture patterns, including multi-agent systems, tool orchestration, memory and retrieval strategies, LLM routing, guardrails, and feedback loops. • Translate these patterns into relevant standards and reusable reference architectures. • Establish and govern DevOps standards across the organization: CI/CD pipeline design, GitOps practices, deployment strategies (blue/green, canary, progressive delivery), environment parity, and release engineering. • Design and oversee platform infrastructure. This includes ECS, Kubernetes clusters (EKS), service mesh, API gateway strategy, secrets management, IAM/RBAC governance, and data stores like DynamoDB, Aurora RDS, Postgres, Elastic/OpenSearch. Additionally, it involves multi-account/multi-region AWS topology. • Lead architecture reviews and provide binding technical decisions on high-risk changes — balancing velocity, reliability, cost, and security. • Define SLOs/SLIs/error budgets, logging standards, distributed tracing, capacity planning, and incident response frameworks. • Introduce new technologies through structured PoC and risk assessment processes; build internal communities of practice around architectural patterns. • Produce architecture decision records (ADRs), system context diagrams, threat models, and runbooks that serve as the source of truth for platform design. • Be a technical advisor to Product and Partners — translating architectural constraints and capabilities into clear strategic options. • Mentor staff and senior engineers on architectural thinking, systems design, and engineering leadership; conduct design reviews that raise the technical bar across teams.
• Architect, build, and maintain AI‑first web and mobile applications using modern frameworks and engineering best practices. • Lead the development of AI‑powered features using Python, LangGraph, and modern LLM tooling. • Design and implement agentic workflow applications, including orchestration, tool use, stateful flows, and human‑in‑the‑loop patterns. • Develop end‑to‑end solutions across the front end, back end, APIs, and cloud infrastructure. • Write clean, scalable, and maintainable code in TypeScript (Node), JavaScript (React), and Python using established design patterns. • Optimize applications for speed, scalability, reliability, and long‑term maintainability. • Work closely with cross‑functional teams to define, design, and ship new features with strong ownership of outcomes. • Provide architectural guidance, code reviews, and mentorship to engineering teams. • Partner with clients to lead demos, support rollout discussions, and ensure successful adoption of AI‑powered solutions.
• Architect, build, and maintain AI‑first web and mobile applications using modern frameworks and engineering best practices • Lead the development of AI‑powered features using Python, LangGraph, and modern LLM tooling • Design and implement agentic workflow applications, including orchestration, tool use, stateful flows, and human‑in‑the‑loop patterns • Develop end‑to‑end solutions across the front end, back end, APIs, and cloud infrastructure • Write clean, scalable, and maintainable code in TypeScript (Node), JavaScript (React), and Python using established design patterns • Optimize applications for speed, scalability, reliability, and long‑term maintainability • Work closely with cross‑functional teams to define, design, and ship new features with strong ownership of outcomes • Provide architectural guidance, code reviews, and mentorship to engineering teams • Partner with clients to lead demos, support rollout discussions, and ensure successful adoption of AI‑powered solutions.

