Consultant - Backend & Agentic AI Engineering

Chryselys; Hyderabad; Hybrid; INR 450,000 - 800,000; Full time

Job summary

Chryselys is seeking an experienced Backend & Agentic AI Engineer to design, build, and scale AI-enabled platforms. You will contribute across Python/Node.js backends, GenAI, RAG pipelines, and semantic layers for enterprise environments.

The role emphasizes reliability, security, observability, and collaboration with product and data science teams to translate complex requirements into scalable technical solutions.

Qualifications

• 7–9 years of backend engineering experience, building scalable APIs and data-intensive platforms.
• Hands‑on development in Python and/or Node.js.
• Minimum 2.5 years of practical Agentic AI / Generative AI / RAG experience.
• Experience taking AI-enabled systems from concept to production with reliability and security.

Responsibilities

• Design, build, and scale backend systems for GenAI, RAG, and semantic layers.
• Develop robust services and APIs using Python and/or Node.js with performance in mind.
• Build semantic layers enabling enterprise knowledge access across entities and metadata.
• Implement RAG pipelines: ingestion, chunking, embeddings, indexing, semantic search, hybrid retrieval, grounding, and response generation.
• Engineer agentic workflows: planning, tool usage, orchestration, memory, task routing, multi-step reasoning.
• Define guardrails for safety, prompts, and tool execution governance.
• Build observability modules with tracing, logging, metrics, and failure analysis.
• Evaluate system performance with offline/online methods, datasets, and feedback loops.
• Collaborate with product, data science, and platform teams to translate requirements into scalable solutions.

Skills

Python

Node.js

TypeScript

REST APIs

Distributed systems

GenAI & Agentic AI

LLM integration

Tool calling

Prompt engineering

Observability

Security

Tools

LangChain

LangGraph

LlamaIndex

CrewAI

AutoGen

Pinecone

Weaviate

Milvus

OpenSearch

Elasticsearch

pgvector

Job description

Role Overview

We are seeking an experienced Backend & Agentic AI Engineer with 79 years of backend engineering experience across Python and/or Node.js, including at least 2.5 years of hands‑on experience building production‑grade GenAI, RAG, semantic layer, and agentic AI systems. The ideal candidate can design, build, scale, observe, evaluate, and continuously improve AI‑enabled platforms that operate reliably in enterprise environments.

Experience Requirements

• 7–9 years of professional backend engineering experience, preferably building scalable APIs, services, data-intensive platforms, and distributed systems.
• Strong hands‑on development experience in Python and/or Node.js.
• Minimum 2.5 years of practical experience in Agentic AI, Generative AI, RAG systems, semantic search, semantic layer design, or LLM‑powered enterprise applications.
• Proven experience taking AI‑enabled systems from concept to production, including reliability, security, monitoring, and performance considerations.

Key Responsibilities

• Design, build, and scale backend systems that support GenAI, RAG, semantic layer, and agentic AI use cases.
• Develop robust services and APIs using Python and/or Node.js with strong attention to performance, maintainability, and production readiness.
• Build semantic layers that enable structured access to enterprise knowledge, business entities, metadata, and domain concepts.
• Implement RAG pipelines including document ingestion, chunking, embeddings, indexing, semantic search, hybrid retrieval, ranking, grounding, and response generation.
• Engineer agentic workflows involving planning, tool usage, orchestration, memory, task routing, and multi‑step reasoning patterns.
• Define and implement guardrails for safety, security, prompt injection protection, hallucination reduction, policy compliance, and controlled tool execution.
• Build observability modules for AI systems, including tracing, logging, metrics, prompt/response monitoring, retrieval quality tracking, latency, cost, and failure analysis.
• Evaluate and improve system performance using offline and online evaluation methods, golden datasets, retrieval metrics, LLM quality metrics, feedback loops, and experimentation.
• Collaborate with product, data science, platform, and business stakeholders to translate complex requirements into scalable technical solutions.

Technical Skills

• Languages: Python, Node.js, TypeScript/JavaScript.
• Backend Engineering: REST APIs, microservices, asynchronous processing, distributed systems, caching, queues, service reliability, and scalable system design.
• GenAI & Agentic AI: LLM integration, prompt engineering, tool calling, agent orchestration, multi‑agent workflows, planning patterns, and AI workflow frameworks.
• RAG & Semantic Systems: embeddings, vector databases, semantic search, hybrid search, metadata filtering, re‑ranking, knowledge retrieval, grounding, and semantic layer design.
• Cloud & Deployment: containerized services, CI/CD, cloud‑native deployment patterns, secure API integration, and production monitoring.
• Observability & Evaluation: AI tracing, telemetry, evaluation datasets, retrieval precision/recall, hallucination tracking, response quality scoring, latency/cost optimization, and continuous improvement loops.

Must-Have Capabilities

• Strong backend engineering foundation with proven ability to build scalable, secure, and maintainable systems.
• Hands‑on implementation experience with semantic layers, RAG pipelines, and enterprise knowledge retrieval systems.
• Practical exposure to agentic engineering, including workflow orchestration, tool integration, and controlled autonomous execution.
• Ability to define guardrails and governance mechanisms for safe and compliant AI behavior.
• Ability to instrument AI systems with observability, diagnostics, monitoring, and feedback capture.
• Ability to evaluate AI system quality and improve retrieval accuracy, response relevance, latency, reliability, and cost efficiency.

Good-to-Have Skills

• Experience with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar orchestration frameworks.
• Experience with vector databases and search platforms such as Pinecone, Weaviate, Milvus, OpenSearch, Elasticsearch, pgvector, or similar technologies.
• Experience with cloud AI services, secure enterprise integrations, identity and access controls, and data privacy requirements.
• Exposure to healthcare, life sciences, pharma data, commercial analytics, or regulated enterprise environments.