Principal Applied AI Engineer

Hucon Solutions; Hyderabad; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Hucon Solutions in Hyderabad, India, seeks an experienced Applied AI Engineer to lead the design and implementation of multi-step reasoning chains and agentic RAG pipelines using LangGraph and structured output patterns.

You will build safeguard mechanisms, integrate with MCP for grounded knowledge access, mentor the team, and collaborate with EU partners to ensure compliant, scalable deployments in cloud environments (GCP).

Qualifications

• Bachelor's or Master's in CS, AI with 5+ years building production AI/ML systems.
• Expert-level Python and practical experience with LangGraph and agentic RAG architectures.
• Experience implementing AI safety measures including prompt injection defence and hallucination mitigation.
• Strong knowledge of MCP, LLM orchestration patterns, and Claude.
• CI/CD, Docker/Kubernetes, and cloud (GCP) in production environments.

Responsibilities

• Lead design and implementation of complex multi-step reasoning chains and RAG pipelines.
• Architect safeguarding mechanisms for prompt injection defence and hallucination mitigation.
• Mentor Applied AI Engineers in Hyderabad, conduct reviews and enforce standards.
• Integrate AI components with MCP for grounded, auditable knowledge access.
• Collaborate with Germany-based AETHER teams to embed AI services into CI/CD pipelines.
• Ensure deployment, observability, and compliance with EU AI Act and DORA.
• Continuously evaluate prompts, retrieval mechanisms, and model configurations for accuracy and latency.

Skills

LangGraph

Agentic RAG

Python

LLM orchestration

Structured output

AI safety

CI/CD

Docker

Kubernetes

GCP

Anthropic Claude

Education

Bachelor's or Master's in CS/AI

Tools

Docker

Kubernetes

GCP

GitHub Actions

Anthropic Claude

Job description

Role & responsibilities

• Lead the design and implementation of complex multi-step reasoning chains and agentic RAG pipelines using LangGraph and structured output patterns.
• Architect and enforce safeguard mechanisms including prompt injection defence,
• hallucination mitigation, and context-window management across all AI agents.
• Serve as the technical reference for Applied AI Engineers in Hyderabad,
• conducting code reviews, mentoring on best practices, and driving engineering
• standards.
• Integrate AI components with the Model Context Protocol (MCP) to ensure
• agents access a shared, grounded knowledge base with reliable and auditable
• outputs.
• Collaborate with Germany-based AETHER teams to embed AI services into
• CI/CD pipelines, ensuring seamless deployment, observability, and compliance
• with EU AI Act and DORA requirements.
• Continuously evaluate and optimise prompt strategies, retrieval mechanisms,
• and model configurations to improve agent accuracy, latency, and reliability at
• enterprise scale.

Preferred candidate profile

• Bachelor's or Master's degree in Computer Science, AI, or a related field, with 5+
• years of hands‑on experience building production AI/ML systems.
• Expert-level Python programming skills with deep practical experience in
• LangGraph, agentic RAG architectures, and structured output design patterns.
• Proven ability to implement AI safety and quality mechanisms including prompt
• injection defence, hallucination mitigation, and context-window management in
• production environments.
• Strong understanding of the Model Context Protocol (MCP), LLM orchestration
• patterns, and foundation models such as Anthropic Claude.
• Solid experience with CI/CD integration, containerisation (Docker/Kubernetes),
• and DevSecOps practices in cloud environments (GCP preferred).
• Nice-to-have: Experience in regulated industries (financial services, EU AI Act,
• DORA), familiarity with GitHub Actions and enterprise-scale repository
• ecosystems, German language skills.